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

The annotations already declare this as a safe, idempotent, read-only, non-destructive computation, so the safety profile is covered. The description adds the 21h-6h window and lists return fields, but the latter duplicates the existing output schema, so little genuinely new behavioral context is contributed.

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?

Three short clauses, front-loaded with the core purpose, time window, and then secondary details. The inline return-value list is largely redundant given the output schema, which slightly dilutes the efficiency.

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 pure calculator with full param coverage, an output schema, and annotations covering the safety profile, the description supplies everything needed to invoke it correctly. Only minor operational detail (e.g., that the base rate is in euros) lives solely in 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%, with units, defaults (25%), and bounds all documented in the schema. The description only echoes that the premium percentage is configurable, adding no meaning beyond the schema, so the baseline of 3 applies.

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?

States a specific verb and resource ('calculate night shift pay') plus a concrete scope constraint (21h-6h) and the configurable premium, which is enough to place it apart from generic payroll calculators like calculate_overtime_pay_fr. It never names a same-task sibling, though, so the differentiation is implicit rather than explicit.

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?

There is no explicit when-to-use or when-not-to-use statement, and no comparison to adjacent tools (overtime, salary, add_hours). The only routing hint is the pointer to list_bundles for related 'temps-rh' calculators, which gives partial navigation but does not tell an agent when this tool is the right pick.

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