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

Annotations already declare readOnly, idempotent, non-destructive, openWorld, so the safety profile is covered. The description adds real behavioral context beyond that: the 'Personal data (absence)' privacy flag and the constraint that year/month must be supplied together to scope the period. It stops short of describing result ordering or paging behavior, but the additions are substantive.

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 what the tool returns, followed by the one non-obvious usage rule and a compact endpoint reference. Nothing is padded, though the raw GET path is borderline redundant for an agent that only needs selection and invocation cues.

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 read-only list tool with 8 optional parameters and full schema coverage, the description supplies the returned fields, the period-restriction rule, the privacy classification and the underlying endpoint, while annotations carry the safety profile. There is no output schema, but the field list in the description covers what an agent needs to know about the response shape.

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 100%, so the baseline is 3, but the description adds a cross-parameter rule the schema does not express: year and month must be given together to restrict to a period. That is meaningful semantics beyond the individual field docs. The remaining parameters (top, skip, filter, orderby, count) are left entirely to 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?

States a specific verb and resource ('List employee leave applications') and enumerates the returned fields (type, dates, days, status), so the agent knows exactly what data comes back. It does not explicitly distinguish itself from close siblings like payspace_list_leave_adjustments or payspace_list_leave_entitlements, leaving that differentiation to the names alone.

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 sentence 'Give year and month together to restrict to a period' gives one concrete usage rule, which is genuinely helpful. However, there is no guidance on when to prefer this over the leave-adjacent siblings, no mention of prerequisites (e.g. company_id resolution), and no when-not-to-use conditions.

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