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

Annotations only cover the safety profile (readOnly, idempotent, non-destructive), and the description goes well beyond that: it discloses the training source (PNCP homologated winners), the per-item limit (up to 99 highest-value items, 3 CNAEs each), the 3/2/1 positional scoring, the fallback when no items exist (5 most probable, no itens/valor_estimado fields), the cost (free), and a measured accuracy figure (87% as of 27/09/2026).

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?

Front-loads the purpose, then layers useful behavioral detail (fallback, limits, accuracy, alert CTA). It is dense and slightly long, with some promotional phrasing ('Grátis'), but almost every sentence carries selection-relevant information.

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?

With no output schema, the description does the work of describing return shape (CNAE list, ranking, official description, counts, estimated value share) and the special fallback case. Accurate enough for an agent to call and interpret results, though it does not discuss pagination or error/empty-result handling directly.

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 100% for the single 'id' parameter ('id da compra (vem da busca)'), so the schema already carries the semantics. The description confirms it operates on a purchase but adds no formatting or sourcing detail beyond the schema, establishing the baseline 3.

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?

States a specific resource and scope: the CNAEs most likely to win a purchase like this, ranked, with official description and per-CNAE item/value counts. An agent can immediately understand this is a CNAE-recommendation tool and tell it apart from generic search (buscar_licitacao) or company lookup (buscar_empresa) siblings.

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?

Gives clear context (use on a purchase to see likely winning CNAEs, free of charge) and routes the agent to an alternative workflow for a related need: create an alert via POST /api/alertas to receive future purchases of those CNAEs. It lacks explicit 'when not to use' exclusions, but the alternative is named.

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