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

Annotations already mark the operation as read-only, idempotent, and non-destructive, and the description adds valuable runtime behavior beyond that: it explains the return shape (`{ tabela, count, total, linhas }`), the truncation semantics (`count < total` means results were cut off by `limite`), and the behavior when `filtro` matches nothing. This is exactly the kind of behavioral context that helps an agent interpret results correctly.

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 well-structured: purpose, domain lists, return semantics, usage timing, alternatives, and examples all earn their place. It front-loads the core action and follows with supporting detail in a logical order. The repeated enum values are acceptable because the description adds grouping and semantics not present in the schema.

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 table-lookup tool with three parameters, an output schema, and a well-covered input schema, the description is complete: it lists all valid table domains, explains filter and limit behavior, describes the return envelope, gives usage context, and even names the sibling tool for plenary tables. An agent has everything needed to select and invoke the tool correctly.

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 already documents all three parameters at 100% coverage, so the baseline is 3. The description adds meaningful semantic grouping beyond the schema by distinguishing entity domains from type domains and providing concrete examples such as `{ tabela: 'tipos-prazo' }` and `{ tabela: 'siglas', filtro: 'PEC' }`. It also ties `limite` and `filtro` to the count/total return semantics, which is useful but partly redundant with the schema text.

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: 'Consulta tabelas de referência do processo legislativo para resolver códigos/siglas'. It also clarifies the two domain categories (entity tables vs. type tables) and explicitly separates itself from `senado_tabelas_plenario`. However, it does not differentiate itself from the similarly named sibling `senado_tabelas_referencia`, which leaves some ambiguity about which reference-table tool to choose.

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 explicitly says to use this tool before filtering in `senado_search_processos`/`senado_processo_detalhe`, and it gives a clear when-not-to-use directive: plenary tables belong to `senado_tabelas_plenario`. This gives an agent concrete routing guidance rather than leaving it to infer the intended context.

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