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

Annotations already declare the safety profile (readOnly, idempotent, non-destructive), and the description adds non-obvious interpretive context beyond them: position is WITHIN SEGMENT not market, the share/total denominator is the LEVES recorte (autos + comerciais leves) and not the whole market, and `denominador` carries the exact wording. The catalog link is stated to be by MODEL, never version. These caveats materially change how the returned numbers must be read.

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?

Purpose is front-loaded in the first sentence, then the sentence-per-mode structure parses cleanly and every sentence carries information. It is dense but not padded; the only cost is that the mode cases are run together in prose rather than bulleted.

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 5-parameter, read-only stats tool with no output schema, the description covers all three invocation modes, the denominator caveat, the segment-vs-market distinction, and the model-level catalog linkage. Nothing an agent needs to call and correctly interpret the result is missing.

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%, so the schema already documents each parameter (baseline 3). The description goes further by explaining how parameters combine and interact — that `marca` alone yields brand aggregates, `modelo` is only valid with `marca`, and `grupo` is ignored in those cases — which is genuine added meaning over the per-field schema text.

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 states a specific resource (emplacamentos de veículos 0km) and then enumerates the exact output for each argument combination, so an agent knows precisely what the tool returns. It is clearly distinct from the sibling lookup tools (marcas, modelos, versões, fipe), which resolve catalog entities rather than registration statistics.

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 mode-selection map: no args = ranking, `marca` only = brand total/share/position, `marca`+`modelo` = model number and in-segment position. It also states that `grupo` is ignored when marca/modelo are supplied, removing the ambiguity an agent would otherwise resolve by trial.

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