> ## Documentation Index
> Fetch the complete documentation index at: https://docs.bedrock.cv/llms.txt
> Use this file to discover all available pages before exploring further.
# Best Practices
> Tips for getting the best results from the Bedrock MCP.
## Recommended Tool Flow
For most queries, follow this progression:
1. **Discover** -- `Query` with `entity: "project"` to find the right project, then `entity: "drawing"` to see what's uploaded
2. **Explore** -- `Query` with `entity: "sheet"` to browse sheets and their block structure
3. **Search** -- `Search` for natural language queries, `Ask` for direct questions
4. **Drill down** -- `Query` with `entity: "block"` for OCR, metadata, overlays; `entity: "feature"` for rooms, doors, symbols
5. **Visualize** -- `ViewImage` to convert storage URIs to viewable URLs
6. **Compare** -- `Compare` to diff revisions, `Parse` to extract features, `PollJob` to poll
If the user already provides a project ID or sheet number, skip the discovery step.
## Prompt Tips
### Be specific about sheet numbers
The agent performs better with explicit sheet references. Discipline codes and sheet numbers eliminate ambiguity.
| Prompt | Quality |
| ------------------------------------------------ | ----------------------------------------------------- |
| "What's on the electrical drawings?" | Vague -- many sheets, unclear intent |
| "How many duplex receptacles are on E-201?" | Specific -- one sheet, one feature type, clear metric |
| "What changed on A-101 between Rev A and Rev B?" | Specific -- two revisions, one sheet |
### Use discipline codes
When referring to trades, use standard discipline codes. The agent maps these directly to the `discipline` filter.
| Code | Discipline |
| ---- | --------------- |
| `A` | Architectural |
| `S` | Structural |
| `M` | Mechanical |
| `E` | Electrical |
| `P` | Plumbing |
| `FP` | Fire Protection |
### Ask for one thing at a time
Multi-part questions ("count receptacles on E-201 AND check fire ratings on A-101") often produce better results as separate prompts. Each focused question maps to a clean tool call sequence.
## Context Management
### Use progressive disclosure
Do not request heavy data unless needed. The `include` parameter controls token cost.
```json theme={null}
{
"entity": "block",
"project_id": "proj_oak",
"sheet_number": "A-101",
"type": "Plan"
}
```
Returns block summaries with relations. Low token cost.
```json theme={null}
{
"entity": "block",
"project_id": "proj_oak",
"id": "blk_door_sched",
"include": ["metadata"]
}
```
Adds structured schedule rows. Medium token cost.
```json theme={null}
{
"entity": "block",
"project_id": "proj_oak",
"id": "blk_notes",
"include": ["ocr"]
}
```
Adds full OCR text. High token cost -- can be thousands of tokens for general notes.
A good pattern: start with the default response, let the agent read relations and metadata to understand the data structure, then selectively request `include` fields only for the specific blocks that need them.
### Let pass-through filters do the work
Instead of resolving entity IDs manually, use pass-through filters to skip round-trips:
```json theme={null}
// Instead of: Query entity:"sheet" to get sheet ID, then Query entity:"feature" with sheet_id
// Do this:
{
"entity": "feature",
"project_id": "proj_oak",
"sheet_number": "E-201",
"type": "duplex_receptacle"
}
```
Available pass-through filters:
* `entity: "block"`: `sheet_number`, `drawing_id`
* `entity: "feature"`: `sheet_number`, `block_type`, `block_identifier`, `grid_intersection`
## Error Handling
All tools return errors in a consistent shape:
```json theme={null}
{
"error": "not_found",
"message": "Sheet E-999 not found in project proj_oak"
}
```
| Error Code | Meaning | Recommended Action |
| ------------------- | --------------------------------------------------------- | ------------------------------------------------------------- |
| `not_found` | Entity does not exist or is not accessible | Verify the ID or filter values; check project scope |
| `invalid_input` | Bad parameters (invalid filter combination, unknown type) | Review the parameter values and types |
| `credits_exhausted` | Insufficient credits for vision operations | Alert the user; vision operations (`Compare`) require credits |
| `job_failed` | Async job encountered an error | Check the error message; retry or report to the user |
The `credits_exhausted` error only applies to the `Compare` and `Parse` tools. The `Query`, `Search`, `Ask`, `ViewImage`, and `PollJob` tools do not consume credits.
## Performance Tips
### Batch feature queries by sheet
When analyzing multiple feature types on the same sheet, combine them into fewer calls:
```json theme={null}
// Query all features on E-201 at once
{
"entity": "feature",
"project_id": "proj_oak",
"sheet_number": "E-201"
}
```
Then filter in the agent's reasoning rather than making separate calls for each feature type.
### Use grid\_intersection for cross-discipline queries
Instead of querying each discipline separately and correlating results manually, use the `Query` tool's `grid_intersection` filter:
```json theme={null}
{
"entity": "feature",
"project_id": "proj_oak",
"grid_intersection": "B-3",
"include": ["parent_chain"]
}
```
This returns features from all disciplines at that grid location in a single call. The backend handles the spatial math.
### Sort comparison results by score
After a comparison completes, the `PollJob` results include a `score` for each overlay. Lower scores indicate more changes. Focus on low-score sheets first:
```json theme={null}
// From PollJob result:
{
"overlays": [
{ "score": 0.82, "block_b": { "sheet_number": "A-101" } }, // Most changes
{ "score": 0.97, "block_b": { "sheet_number": "A-102" } } // Minimal changes
]
}
```
Drill into the A-101 overlay first with `Query` with `entity: "block"` and `include: ["overlays", "changes"]`.
## Next Steps
Full parameter documentation for all seven tools.
See complete tool call sequences for real construction queries.