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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds only 'Returns best plan with day count', a thin return hint that an output schema already covers; no insight into computation assumptions or constraints.

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?

Four short sentences with the core purpose front-loaded, which is good. But the trailing 'See list_bundles for related voyage calculators' sentence earns little and injects a confusing reference; trimming it would tighten the definition.

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 simple two-parameter, read-only tool and an output schema, the burden is light, yet the description still fails the basics by naming parameters that do not exist and by not distinguishing itself from calculate_vacation_days_fr. The parameter mismatch alone leaves an agent unable to call the tool reliably from the description.

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?

The description declares inputs as 'vacation days, country, year', but the schema has no country or year parameter at all – it takes public_holidays_count and vacation_days_available. An agent following the description would try to pass parameters that do not exist, which is actively misleading despite 100% schema coverage.

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+resource ('Compute optimal vacation usage by chaining bridge days with public holidays') that is meaningfully distinct from a plain leave-days counter. However, it never names its closest sibling (calculate_vacation_days_fr or calculate_leave_days), so the agent cannot tell from the description alone which of the near-identical vacation calculators to pick.

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?

'Use for HR or worker planning' names an audience, not a condition for selecting this tool over alternatives. The pointer to list_bundles for 'voyage calculators' is a listing tool, not an alternative calculator, and reads like noise rather than routing guidance.

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