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

Annotations already declare destructiveHint=true, idempotentHint=false and readOnlyHint=false, so the safety profile is covered. The description goes beyond that by disclosing two non-obvious traits: the reason text is visible to the employee, and the action is attributed to the 'API Employee' actor in the audit trail. It stops short of saying whether rejection is reversible or what happens on an already-decided request.

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 sentences, front-loaded with the operation class and verb, with every clause carrying information: mutability, precondition, employee-visible side effect, audit attribution, and endpoint. No filler.

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 two-parameter write tool whose annotations already flag destructiveness and non-idempotency and that has no output schema, the description covers the essentials plus audit and visibility context. It is only marginally incomplete on state-transition behavior (e.g., rejecting an already-approved request).

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 the schema already explains both parameters, including that rejection_reason is shown to the employee and where the id comes from. The description's phrase 'a reason the employee will see' simply restates the schema, adding little beyond the baseline.

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 ('reject a pending leave request') with the scope qualifier 'pending', and is trivially distinguishable from its sibling breathehr_approve_leave_request. The 'WRITE:' prefix plus the POST path make the operation's nature unambiguous.

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?

The word 'pending' implies a precondition that the request must still be awaiting decision, which is genuinely useful selection context. However, it never names the alternative (breathehr_approve_leave_request) or states what to do when a request is not pending, so the when-to-use guidance is only implied.

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