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

Annotations already declare non-idempotent, destructive, open-world writes, and the description reinforces this with "Each call creates a new request" plus genuinely new context: the request enters the account's approval workflow and the employee's approver is notified. It stops short of saying what happens on overlapping/duplicate leave or whether the write can be undone.

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?

Short, front-loaded with the WRITE marker and the core action, then four tight clauses covering default type, approval flow, notification, and non-idempotency, ending with the 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 9-parameter mutation with no output schema and rich annotations, the description covers the workflow consequences well (pending request, approval rules, approver notification, non-idempotency). It does not say what the call returns (e.g. a request id) or how failures surface, which leaves a small gap for an agent chaining calls.

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 nine parameters are already documented (types, defaults, date patterns, half-day flags). The description only restates the default type (Holiday) and adds nothing about date format, half-day interaction, or the notes field, so the baseline of 3 applies.

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 opens with an explicit verb+resource ("request leave for an employee") and a WRITE marker, and the note that it "is created as a request, then follows the account's approval rules" cleanly separates it from sibling operations like breathehr_approve_leave_request and breathehr_reject_leave_request. An agent can tell what this does without opening the schema.

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?

Usage is implied rather than stated: the description makes clear this creates a pending request (as opposed to approving/rejecting), but never names the alternative tools or states when to prefer listing/getting a request instead. No exclusions or prerequisites (e.g. valid employee, available allowance) are given.

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