audit_blueprint_health

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations provide destructiveHint=true and readOnlyHint=false, signaling mutation risk. The description adds significant value beyond that: it discloses that the tool runs synchronously, that max_results is a hard cap, that it returns only a summary plus a report path, and that find_erroring_blueprints should be used to avoid recompilation. The schema's force parameter description already covers the PIE refusal and potential editor crash. The description does not repeat that but adds the scoping and return-format context, earning a 4.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but front-loaded with the core purpose. Every sentence carries useful information: the compile-sweep nature, the scoping advice, the return summary, and the alternative tool. It is not padded, though the return type declaration adds a minor structural redundancy with the prose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (4 params, mutation, synchronous execution) and the lack of an output schema, the description is largely complete. It explains the output shape (summary plus report path), the need to read detail with read_mcp_audit_file, and the behavioral risk. It does not describe what 'error/warning counts' mean or the report file format, which is a minor gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema fully documents all four parameters. The description mentions folder_path scoping and max_results as a hard cap, but this largely mirrors what the schema already states. Baseline 3 is appropriate when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: 'Project-wide compile-sweep: RECOMPILES every Blueprint under folder_path and records error/warning counts.' It also distinguishes itself from the sibling find_erroring_blueprints by explaining that the alternative finds broken Blueprints without recompiling. An agent can tell these tools apart without reading either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says when to use this tool ('it compiles, it does not just read metadata') and when to use an alternative ('To find already-broken Blueprints WITHOUT recompiling anything, use find_erroring_blueprints instead'). It also provides operational guidance ('ALWAYS scope it with folder_path on a large project').

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.