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

readOnlyHint=true already declares the safety profile, so the description only needs to add beyond that. It contributes pagination context (offset semantics, page-size cap) and the status-code table, but discloses nothing about permissions, result ordering, or caps on result volume.

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?

Front-loaded with purpose, followed by the filter/status reference and the endpoint. Every clause is dense but earns its place; 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?

Covers the searchable dimensions, status enumeration, time-unit semantics, and pagination handoff. No output schema exists, so return shape is unexplained, and the mismatch between the description's 'LeaveRule'/'Start'/'End' naming and the schema's parameters is a minor completeness gap.

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%, but the schema's status parameter only says '0-5, see description' — the actual code-to-meaning mapping exists solely in the description, so the description carries real semantic weight there. It also clarifies Start/End as unix and LeaveRule as the leave-type id, though it uses the name 'LeaveRule' which does not match the schema's employee_id/location_id/from/to names.

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?

Starts with a specific verb+resource ('Search leave requests') and enumerates the four filter dimensions (employee, location, status, time window). An agent can distinguish it from deputy_create_leave_request without opening either 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?

The filter list implies when this tool is useful (querying existing leave), but there is no explicit when-to-use statement, no prerequisites, and no named alternative such as deputy_query_resource or deputy_create_leave_request. Usage is implied rather than stated.

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