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

Annotations already carry the safety profile (readOnlyHint=true, idempotentHint=true, openWorldHint=true, destructiveHint=false), lowering the burden on the description. The description adds an operational detail: "a live GET against the public IBGE Malhas API", which conveys that no authentication is needed and that the operation is a network read. It consistently reinforces the annotations rather than contradicting them; only rate-limit and error behavior are unaddressed, which is minor for a public read-only endpoint.

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 long but every section earns its place for a 6-parameter tool with non-obvious locality semantics; it uses bullet groups and short headers to stay scannable and front-loads the core purpose before details. Minor redundancy exists where the Features list restates the formato/qualidade enums already present in the schema, but no section reads as filler.

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 complex tool with 4 enum parameters and intricate locality/resolution semantics, the description covers the hard parts: formats, locality codes, resolution levels, quality options, worked examples, and alternative-tool routing, and it states the return behavior. The output schema exists, so return-value structure needs no elaboration. The only gap is the interaction between `tipo` and `localidade` (which overrides which) and the conditional `intrarregiao` filter, both left to the schema.

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 baseline is 3, but the description adds genuine meaning beyond the schema: it decodes locality values ('BR'/'1' = Brazil, state abbreviations, state codes, 7-digit municipality codes) and resolution semantics (0=outline, 2=states, 5=municipalities), with worked examples mapping parameters to real use cases. The `tipo` and `intrarregiao` parameters remain schema-only, but their schema descriptions are adequate.

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?

Opens with a specific verb+resource: "Gets geographic meshes (maps) from IBGE" in three named formats, which is far beyond the minimal title "Malhas geográficas". It also explicitly distinguishes itself from the sibling ibge_malhas_tema by noting what it is not (thematic meshes). An agent can tell exactly what this tool produces without opening the schema.

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?

Provides concrete routing examples ("Brazil with states: localidade="BR", resolucao="2"") that demonstrate when to call this tool. It includes an explicit exclusion clause — "Use a different tool when: Thematic meshes... → ibge_malhas_tema" — which routes the agent to the correct sibling without requiring the sibling's schema. This is the strongest form of usage guidance: when-to-use and when-not-to-use are both stated.

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