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

With no annotations provided, the description carries the full behavioral burden and exceeds it: it discloses the Q4 absence ('O 4º TRIMESTRE NÃO VEM'), the deliberate no-derivation policy for Q4, the sector-specific indicator gaps for banks and insurers ('Banco e seguradora recebem só margem líquida e ROE'), and the conditional API-key requirement. These are non-obvious facts an agent cannot infer from the schema and are exactly the kind of behavior that prevents failed or misinterpreted calls.

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 purpose is front-loaded in the first sentence, followed by four short paragraphs each with a single job: when to use, the Q4 caveat, the sector limitation, and the auth requirement. Every sentence earns its place — even the rationale for not deriving Q4 ('número calculado por nós não entra na mesma lista dos que a companhia reportou') prevents the agent from wrongly expecting or computing that value. No filler or restatement of the schema.

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?

This tool has real complexity — missing Q4, sector-specific indicator availability, conditional auth — and no output schema or annotations to fall back on. The description covers all the major caveats, the content categories returned, and routes to the correct sibling. The remaining gap is the response shape: since there is no output schema, a brief note on how the quarterly series is structured per period would fully round it out.

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 description coverage is 0%, so the description must compensate for both parameters. It does add real meaning: chave_api's conditional necessity is explained ('WEGE3 gratuita; demais exigem chave_api'), and 'WEGE3' implicitly signals the Brazilian ticker format for the ticker parameter. However, ticker format is never explicitly stated (e.g., 'use the code with exchange suffix'), leaving a small gap for a parameter whose schema entry is bare.

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 states exactly what the tool provides: 'Série TRIMESTRAL de uma AÇÃO: contas da ITR, preço do trimestre e indicadores (margem bruta, margem EBIT, margem líquida e ROE TTM).' This names the resource, its periodicity, and its specific contents, which clearly separates it from the annual-series sibling indicadores_anuais. The only minor stylistic point is the absence of an explicit verb, but the noun-phrase structure communicates the return value 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?

The description gives an explicit trigger condition — 'Use quando a pergunta for sobre o ANO CORRENTE ou o trimestre mais recente' — with concrete example queries, and explains WHY the alternative fails ('a série anual só responde depois que o exercício fecha, e fica até um ano defasada'). It also names the alternative directly: 'Para o ano fechado use indicadores_anuais.' This is textbook when-to-use-vs-alternative guidance.

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