Analyse a drawing PDF (Imnoo drawing analysis)

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

Beyond the annotations (openWorldHint, non-idempotent), the description discloses latency (20–120 s), timeout semantics (waits up to timeout_seconds, else returns "processing" with a drawing_id), rate limits, and the privacy/retention behaviour of uploaded files. These are exactly the traits an agent needs before committing to a slow, non-idempotent upload.

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?

Front-loaded with the extraction payload and then the operational constraints, and every clause carries information. Minor waste: the second sentence opens by restating 'analyze_drawing uploads the PDF to Imnoo's drawing analysis' before pivoting to the new rate-limit and retention facts, and the long characteristic enumeration is dense.

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?

There is no output schema, so the description carries the full return-value burden — and it does: per-characteristic feature id, value, PDF page, position and balloon number, plus the title block fields, and the "processing" fallback state. Combined with the timeout and resume mechanics, nothing needed to call or interpret this tool is missing.

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 baseline is 3; the description goes further by explaining the consequence of timeout_seconds (returning "processing" rather than failing), the resume semantics of drawing_id, and the offline-reuse purpose of save_analysis_to. It adds genuine meaning beyond the field descriptions, though it does not restate size/type limits.

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?

The description names a specific verb and resource (analyse a technical-drawing PDF) and enumerates exactly what is extracted: dimensional tolerances, ISO fit classes, threads, GD&T frames, surface finishes, plus title-block fields. This is far more specific than any sibling (load_analysis, build_quality_plan, export_*), so an agent can select it unambiguously.

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?

It states the two entry paths explicitly: upload via pdf_path, or resume an in-flight analysis via drawing_id when a prior call returned status "processing". It also routes to alternatives by name — save_analysis_to/load_analysis for offline reuse — and flags the rate-limit condition (1 free analysis/day per IP, more when signed in).

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