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

Annotations already provide readOnly, idempotent, and non-destructive hints, so the safety profile is covered. The description adds substantial behavioral context well beyond annotations: it explains how overlapping vínculos are counted only once, how special activity is converted to common time with specific EC 103/2019 factors only up to 13/11/2019, and what the return values are. No contradiction with annotations.

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 two dense sentences with no filler. The core purpose and key algorithmic nuances are front-loaded, and every clause adds information about input handling or output. It is an efficient, well-structured description that an agent can parse quickly.

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?

The description explains the main algorithm and return semantics ('tempo total e se atinge o tempo antigo'), which is essential since there is no output schema. It does not specify the exact return format, date formats for inicio/fim, or how missing tipo is treated, but these are minor gaps for an agent selecting and invoking the tool. Given the calculation's complexity and the lack of an output schema, the description is close to complete but leaves a few details to inference.

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 0%, so the description must compensate. It does: 'soma os vínculos' clarifies the vinculos parameter, 'conta concomitância uma vez' defines how overlapping periods are treated, and '35H/30M' implies sexo determines the threshold. However, it doesn't explicitly explain the sexo H/M values or the exact structure of inicio/fim/tipo beyond the schema, so it is strong but not fully comprehensive.

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 verb-resource pair: summing CNIS contribution links and converting special activity to common time. It clearly distinguishes the tool from siblings like calculo_rmi or calculo_pensao because it targets contribution-time computation for old-age benefit eligibility. The inclusion of formula behaviors (concomitance counted once, EC 103/2019 factors) makes the purpose unmistakable.

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 implies the tool is used to compute total contribution time and check whether it reaches the old-age threshold, but it never explicitly says when to choose this tool over a sibling. There is no 'use X instead' guidance or exclusion criteria. The context is clear enough for a rough decision, but explicit routing is absent.

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