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

With no annotations provided, the description carries the full behavioral burden. It discloses a key behavior beyond a simple read: 'Estima a base do FGTS quando não informada' (estimates the FGTS base when not supplied). It also transparently explains the calculation logic for each path, including which components are included. No contradictions exist since there are no annotations. It could have mentioned output format, but the estimation behavior is the main non-obvious trait and is clearly stated.

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 compact: three sentences plus a parameter list. The main purpose and scenario breakdown are front-loaded, followed by parameter guidance. The list of required/optional parameters partially repeats the schema, but the explicit naming instruction earns its place for agent usability. Slight redundancy keeps it from a 5, but it is efficient and well-ordered.

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 calculator tool with 5 parameters and no output schema, the description is largely sufficient. It covers the three scenarios, the estimation behavior, and required/optional parameters. Combined with 100% schema coverage, an agent can invoke it correctly. Missing details like output format or whether all three results are returned at once are minor given the phrase 'nos três caminhos' implies all paths are calculated. It is complete enough for its complexity.

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 all parameter meanings. The description adds value by reiterating which parameters are required vs optional and clarifying that fgts_deposits_base is the base for the fine, but this largely duplicates schema descriptions like 'Omitido, estimamos 8% × salário × meses'. The instruction to use exact English names is helpful but not semantic enrichment beyond the schema.

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 uses a specific verb ('Calcula') and resource ('quanto custa demitir um funcionário CLT') and enumerates the three distinct dismissal paths (sem justa causa, acordo mútuo, pedido de demissão). This clearly distinguishes it from sibling tools like calculate_severance or calculate_fgts by specifying exact scenarios and calculation components (40% FGTS fine, 20% fine, proportional amounts).

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 implicitly defines when to use this tool: for any CLT dismissal cost calculation covering the three named paths. It provides clear context about scope (CLT employees, three termination types) but does not explicitly mention alternative tools or when not to use it. The scenario breakdown gives enough context for selecting it, though it stops short of naming sibling exclusions.

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