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

Goes well past the readOnlyHint/non-destructive annotations: it states that receipts are counted but never returned, that a foreign employee id and a nonexistent id both yield the same 404 (anti-enumeration behavior), the exact scope string "work:read" required, and that an unconnected member is prompted to sign in. Those are the practical failure modes an agent would otherwise hit blindly.

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?

Purpose is correctly front-loaded and the middle sentences (404 behavior, permission, sign-in) each carry real information. However, several clauses are compressed into dense hyphenated fragments ("as the Expenses list shows them — the employee's own claim") and the closing sentence is generic prompt-injection boilerplate that does no work specific to this tool.

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 one-parameter read tool with no output schema, it covers access requirements, failure semantics, and even sketches what a report contains (claims, counted receipts) — enough to call it correctly. It is silent on pagination/result size and on the shape of the returned list, which is the main remaining gap given the absence of an output 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 coverage is 100% and the sole parameter already documents itself as "One of your member's employees, from GET /me/crew." The description reinforces the ownership/scope semantics of employeeId but adds no format, range, or source detail beyond the schema — baseline 3.

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?

A specific verb + resource ("List the expense reports") scoped to "one of your member's employees", which distinguishes it from list_my_expense_reports and from the approval-side siblings. It never names those siblings outright, so an agent must infer the boundary from the possessive phrasing, but the core purpose is unmistakable.

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?

"For a service partner: the expense reports of one employee it supplies" gives useful situational framing, and the permission note implies the caller must be acting for a member. There is no explicit when-to-use/when-not guidance versus get_crew_expense_report (single report) or list_expense_reports_to_approve (approver view), so routing between the crew* and my* expense tools is left to inference.

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