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

Annotations provide only basic flags, so the description adds real value by defining the status transition (pending/approved to rejected) and the reopen path. It does not cover permissions, side effects, or error behavior, but it gives meaningful behavioral context beyond the schema and annotations.

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 contain no filler and front-load the core action. The final parenthetical is slightly awkward but not wasteful.

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 simple two-parameter mutation tool, the description covers the main status behavior and routes to relevant siblings. The lack of an output schema and return-value note is a minor gap, but not critical at this complexity.

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 schema already documents both parameters with 100% coverage, so the description need not repeat them. It adds only 'by id' and a hint that a reason is involved in cancellation, which is marginal beyond the schema.

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?

The description states a specific action and resource ('Reject or cancel a leave request by id') and adds state-transition detail that distinguishes it from leave_approve and leave_cancel. The word 'cancel' slightly overlaps with the sibling name, but the state wording resolves most ambiguity.

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?

It explicitly says a rejected request can be reopened with leave_approve and that leave_cancel should be used for voluntary withdrawal. The conditions are clear, though the parenthetical '(via reject with reason)' leaves some uncertainty about whether leave_cancel is an alias or a separate call.

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