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 adds genuinely useful context beyond that: the 'WRITE:' classification, the fact that the reason is surfaced to the employee, and the underlying HTTP endpoint. It does not explicitly state that the decline is irreversible or what errors occur on an already-declined 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 WRITE classification and the core action, followed by prerequisite and endpoint. Every clause is short and purposeful, though the raw POST path is marginal value for an agent that never constructs URLs itself.

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 destructive mutation with no output schema, the description covers the operation, the prerequisite read, and the user-visible side effect of the reason. It leaves unaddressed what state the request ends in and whether the decline can be undone, which would be worth one more sentence given the destructive hint.

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 all four parameters are already documented, including 'Reason shown to the employee.' The description's 'optional reason the employee sees' largely restates the schema and adds no format or length guidance beyond it. Baseline 3 applies when the schema carries the parameter semantics.

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 verb and resource ('declines a leave request') and scopes it further with the optional reason visible to the employee. The 'WRITE:' prefix immediately separates it from the read-oriented siblings like keypay_get_leave_request and keypay_list_leave_requests, and the action is inherently distinct from keypay_approve_leave_request.

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 gives an explicit prerequisite and names the sibling to use for it: 'Check the request first with keypay_get_leave_request.' That is real routing guidance, not just context. It stops short of stating when-not to use this tool (e.g. use approve instead when the request should be granted).

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