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

Annotations already cover the read-only, non-destructive safety profile, so the bar is lower. The description adds real behavioral context beyond structured data: the default filter to unclaimed items and the toggle to include claimed ones. It omits pagination behavior, but that is already documented in the schema.

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 sentences plus the endpoint path, front-loaded with the resource and the default filtering rule. No filler, though the trailing 'GET /employee_expenses' is low-value trivia rather than guidance.

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?

There is no output schema, and the description compensates by naming the returned fields (date, description, type, amount, VAT, project). Combined with the default-filter explanation and full schema coverage of inputs, an agent has enough to call it correctly.

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%, so page, per_page, employee_id and include_claimed are all documented structurally. The description adds only the include_claimed default semantics, largely restating the schema, so baseline 3 is appropriate.

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 (List) and resource (individual expense items) and enumerates the returned fields. The phrase 'individual expense items' and 'already part of a claim' implicitly separates it from list_expense_claims, but it never names that sibling, so an agent must infer the distinction.

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?

Provides a usable default rule ('by default only unclaimed items; set include_claimed to see all'), which tells the agent how to widen the result set. However, it gives no explicit when-to-use-this-vs-alternatives guidance, notably against the sibling breathehr_list_expense_claims, whose relationship is only implied.

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