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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses that the tool incurs prepaid credit charges, is hosted by the platform, returns only publicly available citizen-level data, and imposes LGPD compliance responsibility on the client. This adds meaningful operational and legal context, though it doesn't cover potential rate limits or error behavior.

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 relatively short, with purpose front-loaded ('Consulta Processual Unificada'), and it packs relevant operational details into two sentences. It is structured but could be broken into clearer points; still, no extraneous wording.

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 simple query tool with two parameters and no output schema, the description covers key aspects like data source, payment, and legal standing, and it benefits from strong annotations. However, it omits parameter details and what the response contains, and it lacks guidance on process number formatting, making it incomplete for robust automated usage.

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?

The input schema has two parameters (numero_processo required, grau optional) with no descriptions; schema coverage is 0% and the description offers no explanation of these parameters. The name 'numero_processo' is self-explanatory, but 'grau' (judicial level) is ambiguous and the description gives no format or usage hints, leaving the agent to guess.

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 identifies the tool as a unified process consultation for TRT from an official source, with the verb 'consulta' and the resource 'processo'. It distinguishes from sibling tools by being a domain-specific query rather than platform utilities like authenticate or connect, though it doesn't specify the exact data returned (e.g., status, parties).

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?

Provides contextual guidance: it mentions the official source, payment via prepaid credits, and that no platform credentials are needed, which helps the agent decide when to invoke it. However, it does not explicitly state when to use it over alternatives or exclude cases (e.g., when the process data is confidential), and no alternative tools are referenced.

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