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

Even with readOnlyHint, openWorldHint, and idempotentHint annotations, the description adds substantial behavioral context: coverage gaps, the empty-result contract (`totalBlocos` 0 with `aviso`), pagination truncation via `aviso`, the 20-block cap in `texto` mode, and mode-specific payload differences. There is no contradiction with the annotations; rather, the description enriches them.

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 dense but every sentence earns its place: return shape, empty-result behavior, coverage, mode semantics, pagination, id provenance, and media alternative. It front-loads the most critical information and organizes the rest in a logical decision order for an agent. Nothing is redundant.

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?

The description is fully self-contained for a complex tool: it covers the return object, error/empty case, coverage exclusions, mode-specific behavior, pagination window, how to obtain IDs, and the correct alternative tool for media. With annotations and an output schema already available, nothing essential is missing.

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?

Although schema coverage is 100%, the description goes far beyond it: it explains that `modo` governs the entire payload shape, that `sequenciaFim` only acts in `texto` mode, that `limite` defaults to 20 with truncation signaled by `aviso`, and that `orador` does partial content matching. These semantics are essential for correct invocation and are not apparent from the raw schema alone.

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: 'Transcrição oficial (notas taquigráficas) de uma sessão plenária ou reunião de comissão, em blocos sequenciais.' It precisely defines the deliverable and distinguishes itself from siblings like senado_videos_taquigrafia (media) and senado_discursos_* (speech-level content). An agent can immediately tell what this tool does and what it does not do.

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 explicit when-to-use guidance: 'Obtenha o id via senado_agenda_plenario/senado_resultado_plenario (sessão) ou senado_reuniao_comissao (reunião)' and 'Para a mídia (vídeo/áudio) use senado_videos_taquigrafia, não esta.' It also tells when notes are not available, such as joint/cancelled/some solemn sessions, so the agent can predict empty results. This is exemplary routing among alternatives.

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