metodologia

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

With no annotations present, the description carries the full behavioral burden and largely delivers: it documents the mode-switching behavior (default list vs. explicit read), the parameter format with a concrete example, and the access properties ('Gratuito — não exige chave'). Missing edge-case behavior like invalid page identifiers, but the disclosed traits substantially outpace the annotation baseline.

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 front-loaded with the essential purpose and then breaks down behavior cleanly in a list-like structure. There is minor redundancy — the two-mode behavior is explained both in the intro bullets and again in the parameter documentation — but every sentence adds real information, and nothing is fluff.

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?

For a low-complexity tool (1 optional parameter, no output schema, no annotations), this description is nearly exhaustive: behavior, usage trigger, parameter semantics, and access model are all covered. The only gaps are minor (error behavior for invalid page names, and the exact shape of the returned listing), which are acceptable given the simplicity.

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 0% — the schema only reveals the parameter name and default. The description carries the full semantic load and succeeds completely: it explains the default behavior ('' lists pages), the page-identifier contract ('exatamente como aparece na listagem'), and gives a realistic example ('roic'). The agent can call it correctly after reading only the description.

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 opening line clarifies the resource ('pública... por trás dos indicadores — como cada número é calculado'), which goes well beyond the terse name 'metodologia' by explaining the tool returns the public calculation methodology behind indicator numbers. The dual-mode behavior (list vs. read page) further sharpens the purpose. It doesn't explicitly differentiate from siblings by name, but the intent is 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?

Explicit guidance is provided: 'Use quando precisar auditar ou justificar um número devolvido pelas outras ferramentas.' This identifies a clear trigger condition and implies the siblings are the tools producing those numbers. Could give slightly more contrast with alternatives (e.g., raw data vs. methodology), but the direction is correct.

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