buscar_compras_publicas

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

With no annotations provided, the description carries the full disclosure burden. It does disclose one genuinely valuable behavioral trait — results are not deduplicated — and the verb 'Pesquisa' implies a read-only search operation. However, it says nothing about pagination, result limits, how multi-source results are aggregated, or filter behavior, so the disclosure is thin for a 10-parameter search tool.

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 a single efficient sentence with no filler: verb, resource, scope, and the deduplication caveat are all front-loaded. Every word earns its place. It is slightly under-sized relative to the tool's 10-parameter complexity, which keeps it from a 5.

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 output schema covers return values, so that side is handled. But the input side is incomplete: 10 parameters, zero schema descriptions, no annotations, and a one-sentence description. An agent cannot determine date formats, whether filters are combinable or mutually exclusive, or which values `fonte` accepts beyond the 'todas' default. This is insufficient for correct invocation.

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%, so the description must compensate but barely does: 'nas fontes catalogadas' only loosely maps to the `fonte` parameter. The required `texto` parameter is never explained, and there is no guidance on how cnpj, uasg, data_inicio/data_fim, modalidade, codigo_servico, or codigo_material behave or combine. Parameter names are self-descriptive in Portuguese, but the description adds essentially no semantic value beyond them.

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 uses a specific verb ('Pesquisa') and names the resource ('compras públicas'), adding scope with 'nas fontes catalogadas' and a distinguishing behavioral trait, 'sem deduplicar resultados.' This separates it from the many id/cnpj-specific consultation siblings even without naming one explicitly. It is clearly more than a tautology of the tool name.

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?

There is no explicit guidance on when to use this broad search versus the dozens of sibling consultation tools (e.g., compras_listar_modulo_contratacoes_* or pncp_obter_*). The 'sem deduplicar resultados' clause hints that it returns raw, unfiltered results, but no alternative tool is named and no condition is stated. An agent must infer the tool's role from context alone.

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