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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true. The description adds meaningful context beyond these: no platform credentials required, pay-per-query prepaid billing model, data is non-confidential public data, and LGPD controller responsibilities. The payment model in particular is valuable operational info that would affect whether an agent warns the user about cost. No contradiction between description and annotations.

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 core function is front-loaded ('Consulta em fonte oficial'), which is good, but the rest is a dense run-on mixing legal, commercial, and platform details into a single paragraph of clauses. Every sentence carries some information, but the structure forces the reader to untangle functional purpose from compliance disclaimers. Could be broken up or pruned.

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 and no description of return values, the agent has no idea what data the query returns (case status, parties, movement history, etc.) or what 'grau' filters. The description heavily over-indexes on legal compliance while under-specifying the functional contract. For a tool with a single required parameter and no documented response, more functional detail is expected despite needing to cover its legal bases.

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% and the description adds no clarification for either parameter. While 'numero_processo' is reasonably self-explanatory, 'grau' (court instance/degree) is a domain-specific Brazilian legal term whose allowed values and format are never clarified. With zero schema coverage and no compensation in the description, the agent is left to guess at the semantics of an ambiguous optional parameter.

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's purpose: 'Consulta Processual' (case lookup) against 'Tribunal TRT5' (the 5th Region Labor Court), specifying a concrete verb+resource. However, the purpose is somewhat diluted within compliance/commercial boilerplate about LGPD and prepaid credit, and there's no explicit sibling differentiation (though siblings are all system tools, making confusion unlikely).

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 implicitly scopes usage: it queries non-confidential, citizen-accessible data from official Brazilian sources, for which the client is the LGPD data controller with legitimate purpose. This implies appropriate use cases (lawful public record lookups) but never explicitly states when to use this tool over an alternative or specifies exclusions. The guidance is present but implied rather than direct.

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