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

Annotations already declare readOnly/idempotent/non-destructive, and the description layers substantial extra behavior on top: the classifier source, the 3-2-1 positional scoring, the 99-item highest-value cap, the no-items fallback (top 5 without `itens`/`valor_estimado`), a measured accuracy figure (87%), and that it costs nothing. This is unusually rich behavioral disclosure.

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 core claim is front-loaded in the first sentence, and most later detail is genuinely useful (edge cases, accuracy, cost). But the body is a single dense paragraph mixing algorithm internals, fallback behavior, and a measurement date, which is harder to parse than it needs to be.

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 must carry the return contract, and it does: it names the returned CNAEs, their official descriptions, per-CNAE item counts, and estimated-value share, and it explains the reduced shape when there are no items. It is nearly complete, though a clearer note on the single `id` argument's origin would close the last gap.

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?

There is a single required `id` parameter at 100% schema coverage, so the schema already documents it fully. The description confirms it expects a procurement id but adds no syntax, format, or sourcing detail beyond that, so the baseline of 3 applies.

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 opening sentence states a specific resource and result: the CNAEs that usually win procurements like this one, ranked most-likely-first with descriptions and value shares. This is clearly distinct from siblings like list_cnaes or get_procurement, though the description never names a sibling to reinforce the contrast. Purpose is unambiguous but not explicitly differentiated.

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 implies usage (pass a procurement id to see its likely winning activity codes) and notes it is 'Free', plus a downstream path (create an alert to track new procurements of these CNAEs). However, it gives no explicit when-to-use versus alternatives and no when-not guidance, so the routing burden is left to inference.

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