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

Beyond the annotations (readOnlyHint, idempotentHint), the description adds key behavioral details: the shape of the response (`{ codigo, secao, encontro }`), that `encontro` may be an array when upstream returns multiple, that it may be empty if no data for that section, and that it errors on invalid `codigo`. These are useful operational facts not expressed in annotations. No contradictions with 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 description is concise yet information-dense. It front-loads the primary purpose, then logically presents the return structure, the section options, caveats (empty possible, error case), and finally the prerequisite step. Every sentence adds value; there is no fluff or repetition. The structure aids quick comprehension and correct usage.

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 two-parameter read-only tool with an output schema (mentioned in context), the description is remarkably complete. It covers the response structure, the meaning of the enum parameter, edge cases (empty result, invalid code), and the recommended way to obtain the required `codigo`. An agent has all necessary information to invoke this tool correctly without further clarification.

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?

While the schema already provides descriptions for both parameters (100% coverage), the description enriches the meaning significantly. For `secao`, it explains each enum value in detail (e.g., 'detalhes' returns general session data; 'pauta' returns agenda items; 'resultado' returns voted items and outcomes; 'resumo' returns a summary). For `codigo`, it clarifies the source (obtained from other tools) and error behavior. This substantially goes beyond the schema's generic descriptions.

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 opens with a specific verb and resource: 'Detalhes de um encontro legislativo (sessão de plenário)' – clearly stating it returns details of a specific plenary session. It further distinguishes itself from sibling tools by explaining the return structure and that the `codigo` must come from `senado_agenda_plenario` or `senado_resultado_plenario`, which are list/request tools. This unambiguously separates it from the many other `senado_*` tools.

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 provides explicit guidance on when to use this tool: after obtaining a `codigo` from `senado_agenda_plenario` or `senado_resultado_plenario`. It also explains the `secao` parameter's valid values and what each returns, enabling the agent to choose the appropriate section. The note about erroring on a non-existent `codigo` further clarifies proper usage.

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