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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), and the description adds genuinely non-structured behavior: a hard cap of 20 results, the aggregation rule of one result per street per city, and the conditional behavior where a house number present in the query yields the point of that number. What is missing is failure/empty-result behavior and whether results can be expanded beyond 20.

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 dense sentences with the core capability front-loaded and the conditional house-number behavior placed second where it belongs. No filler; slight compression makes the first sentence a little awkward to parse but nothing is wasted.

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 carry the return-shape burden and largely meets it (result cap, deduplication per city, conditional point). Parameters are fully covered by the schema and the read-only nature is declared by annotations. Remaining gaps are edge-case behavior (zero results, pagination) rather than anything blocking a correct call.

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%, so the schema already documents q, uf and cidade, making a baseline of 3 appropriate. The description adds only marginal meaning ('by name (or by neighborhood)'), and neighborhood is not even a schema parameter, which leaves a small mismatch between the prose and the actual inputs.

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?

It states a specific verb and resource ('Finds a street by name (or by neighborhood) in Brazil') plus a scope constraint (up to 20 results, one per street per city). That is far more precise than the bare name 'buscar' or the title 'Find a street'. However, it never names or distinguishes itself from close siblings such as consulta_endereco, proximo, or raio, so an agent cannot tell from the text alone which address tool to pick.

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 explains what a query may contain (street name, neighborhood, house number, city) but gives no when-to-use or when-not-to-use guidance. With siblings like cep, consulta_cep, consulta_endereco, vizinhanca and proximo all in the same address domain, the absence of any routing cue is a real gap.

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