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

Annotations already establish this as a safe read-only, idempotent operation, so the description only needs to add behavioral context beyond that. It discloses that the value is 'dinâmico, IPEADATA', which alerts agents that the data source is external and values may change over time. However, it does not explain what happens when 'ano' is omitted (it is not required), whether an invalid year is handled, or what shape the result takes.

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 a single compact sentence that front-loads the core resource and then adds relevant use-case context. There is no redundancy or filler. It loses one point because it is a fragment rather than a complete, self-contained sentence, but it remains highly efficient.

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 simple single-parameter lookup, the description provides the essential purpose and primary use cases. However, it omits important operational details such as default behavior when 'ano' is absent, the return format, and whether historical years are supported. These gaps are notable because there is no output schema to fill them.

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?

With 0% schema description coverage, the description must compensate for the undocumented 'ano' parameter. It partially does through the phrase 'de um ano', which signals that the parameter is a year. Yet it does not specify the expected format, valid range, optionality behavior, or unit of the result, leaving the agent to infer too much for a parameterized call.

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 the resource and scope clearly: 'Salário mínimo nacional vigente de um ano' identifies the tool as a lookup for a given year's national minimum wage. It also positions the tool within the sibling family by saying it is the 'Base para dosimetria, pensão...' which distinguishes it from the calculation-focused siblings. However, it lacks an explicit verb and does not name a sibling directly, so it doesn't fully reach the top tier.

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 phrase 'Base para dosimetria (dia-multa), pensão por % do SM e mínimo existencial' gives clear usage context: this tool supplies the minimum-wage baseline needed for those other calculations. But it never explicitly states when to use this tool versus alternatives like calculo_dosimetria or calculo_pensao, nor does it mention exclusions or fallback scenarios.

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