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

Annotations already declare a safe read, but the description adds substantial proprietary context: the data comes from CVM open data (ODbL) refreshed WEEKLY, carries date but not time, and the `fonte` field signals file freshness — a critical caveat for a 'latest news' tool. It also bounds expectations explicitly (no summary, no impact analysis, no recommendation; a single descriptive `frase` per item) and notes it is free with no API key.

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 resource, ordering, and returned fields before the parameter and caveat details, which is the right structure. It runs long and a few clauses are dispensable ('Gratuito, sem chave', 'Traz `citacao`'), but nearly every sentence carries operational information.

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?

With no output schema, the description does the job of documenting the return shape (companhia, assunto, data de entrega, protocolo, link, frase, fonte, citacao) plus the freshness limitation. An agent has everything needed to call it and to correctly caveat results as weekly-lagged and reference-only.

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 carry the load: it explains `ticker` as a company filter with an example (PETR4) and pins `categoria` to its two allowed values, which the schema does not declare as an enum. Only `limite` is left wholly unexplained (no default, no cap), which is the one meaningful gap.

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 and resource — the latest Fatos Relevantes / Comunicados ao Mercado delivered to the CVM, ordered newest to oldest — and enumerates the exact fields returned (companhia, assunto, data, protocolo, link). An agent can distinguish this from siblings like fatos_contabeis or eventos without opening any 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?

Usage is implied by the filtering explanation (`ticker` per company, `categoria` for 'Fato Relevante' vs 'Comunicado ao Mercado'), which tells the agent how to narrow results. But it never says when to pick this tool over the many sibling disclosure tools (eventos, fatos_contabeis, reapresentacoes), and offers no exclusions or prerequisites.

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