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

Beyond the annotations, the description discloses critical behavior: the operation is slow (~2 min), it returns a temporary 'arquivo_url', it may return a 'job_id' if not ready, and it supports batch mode. This adds significant operational transparency that annotations alone do not provide.

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 concise and well-structured: three dense sentences convey purpose, async behavior, return values, examples, and bulk support. No redundant or filler content is present.

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?

The description is strong for an async, no-output-schema tool: it covers wait behavior, job fallback, return URL, examples, and batch mode. It falls slightly short by not specifying the exact response shape/status details or the semantics of 'account' and 'filtros', but overall it is sufficiently actionable.

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?

With 0% schema description coverage, the description compensates well by explaining 'report_id' with concrete examples, 'aguardar_segundos' as the inline wait period, and 'report_ids' as batch input. However, it does not add semantics for 'account' or 'filtros', so the compensation is not complete.

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 clearly states the tool's purpose: 'Gera um relatório do CIGAM' and distinguishes it from siblings by emphasizing it is slow, produces an Excel file, and may return a job_id for later polling. It also gives concrete report_id examples, making the resource and scope unmistakable.

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?

The description gives explicit guidance on when to wait inline via 'aguardar_segundos' and when to poll later using 'cigam_job' instead of repeatedly retrying. It also documents the bulk usage path with 'report_ids', providing clear when-to-use and when-to-use-alternative context.

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