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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds the mode-selection/precedence behavior, which is useful, but says nothing about permissions, rate limits, or result shape; and it names a `codigos` parameter the schema does not contain, which muddies the behavioral picture.

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?

Two short sentences, front-loaded with the domain scope and immediately followed by the selection rule — no filler. It loses a point only because one clause is spent on a parameter that does not exist 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 2-parameter tool with an enum, no output schema, and a read-only annotation profile, the mode-selection explanation is the main thing needed and it is present. But the description never says what a resolution returns (canonical code vs. label), and it is internally incomplete by referencing `codigos` that callers cannot pass.

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 coverage is 100% and both real parameters (`q`, `tipo`) are documented in the schema, so baseline 3 applies. The description adds the q-vs-codigos decision rule, but that rule refers to a parameter absent from the schema, so it adds confusion rather than compensating value.

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 names the reference domains (CNAE/município/natureza) and states that it either searches by text or resolves existing codes, so the general purpose (reference lookup/resolution) is inferable. However, the verb is elided to a bare noun-like "Ref" and nothing distinguishes it from siblings like `search`, `suggest`, or `local` that likely do similar lookups.

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?

It gives an explicit either/or usage rule — search with `q` or resolve codes you already hold — plus a precedence rule: `codigos` wins when both are supplied. That is real when-to-use guidance, though it never references any alternative sibling tool.

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