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

Beyond the annotations (readOnly, idempotent, non-destructive), the description elaborates on behavioral details: the full-text search does not return or filter by value, it handles multiple terms via separate searches with intervals to avoid rate limits, and outputs merged deduplicated results. This transparency goes well beyond the basic 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 well-structured: it starts with the primary function, then details the multiple-term behavior, and finally includes an important caveat about value. Despite its length, it is concise and front-loaded, with each sentence adding necessary information. The structure aids readability and comprehension.

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?

Given the lack of an output schema, the description compensates by specifying the returned fields (órgão, estado, município, modalidade, situação, datas, referência) and noting that `termos_buscados` is included. It also explains the tool's limitations (no value) and points to alternatives, providing a holistic understanding of its role. This makes the description sufficiently complete for the given context.

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 has no descriptions (0% coverage), so the description must compensate. It explains the core parameter `termos[]` (and implies `termo` as singular) and the behavior of multiple terms. However, it does not elaborate on `pagina`, `tam_pagina`, `ordenacao`, or `status`, which are common pagination/ordering/filter parameters. While it adds significant meaning for the main search term, it omits some parameter details, so a score of 4 is appropriate.

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 states the tool's purpose: searching licitações by keyword in the object across national scope (editais, atas, contratos). It also distinguishes itself from related tools by noting that it does not return or filter by value, directing users to pncp_listar and pncp_historico for those needs.

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 versus alternatives: it mentions that for value-based filtering/ordering, one should use pncp_listar or pncp_historico. It also explains the behavior with multiple terms (separate searches, merging, deduplication) and the rate-limiting caveat, offering clear usage context.

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