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

Annotations already declare readOnly/idempotent/non-destructive, so the safety bar is met; the description adds real behavior beyond that: deterministic ordering ('latest start first'), inclusion of request_id, date-window semantics ('requests that touch from-to'), and a cost note ('Free'). It stops short of describing pagination behavior (limit defaults to 100, capped at 500).

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?

A single dense sentence, front-loaded with the resource and ordering, then filters, then the escalation hint. Every clause carries information; the telegraphic style ('Free.') is slightly terse but costs nothing.

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 7-parameter read tool with no output schema, the description covers filtering, ordering, and the returned identifier, which is most of what an agent needs. The notable gap is pagination: nothing says results are capped at a default of 100 (max 500) or how to page, which matters for a list tool with zero required params that can return large sets.

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 57%, and the description compensates for the main ambiguity by defining the from/to semantics as an overlap test ('requests that touch from-to') rather than a containment test — that is genuine meaning the schema's bare 'YYYY-MM-DD' does not give. It also ties status to a next action. limit/offset remain undocumented in prose, but their schema defaults and bounds are self-explanatory.

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?

Names the resource (leave requests), the sort order (latest start first), and the returned key (request_id), which is concrete enough for an agent to know what it gets back. The list verb is implied by the tool name rather than stated, and it does not distinguish itself from the other HR read tools such as hr_who_is_out or hr_report.

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 parenthetical '(pending ones wait for hr_decide_leave)' routes the agent to the correct follow-up tool once it has found pending requests, which is useful workflow guidance. However, there is no statement of when to call this versus hr_who_is_out, hr_tasks, or hr_report, and no prerequisite/exclusion guidance.

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