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

Annotations already establish the operation is read-only, idempotent and non-destructive, so the safety profile is covered. The description adds genuine domain behaviour beyond that: the accrual rate, the annual cap and the explicit capped_at_max / days_to_max semantics, which tell the agent what the computation does rather than merely that it is safe.

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?

Two tight sentences, front-loaded with the accrual rule that defines the tool. The enumerated return-field list is somewhat redundant given that an output schema exists, which is minor waste, but the definition is otherwise dense 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?

With a full output schema, complete parameter coverage and complete annotations, the description only needs to supply domain rules and it does so accurately. The one remaining gap is sibling disambiguation against calculate_vacation_days_fr, which is the primary selection risk in this crowded namespace.

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%, and the schema already specifies the YYYY-MM-DD format for start_date and the 1-12 bound for months_worked. The description adds no parameter-level meaning (e.g. how start_date interacts with the reference period), so the baseline 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 a precise resource: French paid leave (congés payés) accrual at 2.5 days/month capped at 25 days. That is far more specific than most siblings in the catalogue. It does not, however, distinguish itself from closely related siblings such as calculate_vacation_days_fr or calculate_vacation_days_optimal, which an agent may reasonably confuse with it.

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 statement of when to use this calculator versus the many other French leave/vacation calculators in the sibling list. The only routing hint — 'See list_bundles for related temps-rh calculators' — points to a bundle browser, not to a decision rule, and does not resolve the ambiguity with calculate_vacation_days_fr.

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