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

Annotations already declare the write/mutating profile, but the description adds what annotations cannot: that the employment record is modified, that intelliHR workflows may fire as a side effect, and that the record is left in an un-finalised state until the person returns. That lifecycle detail is genuinely non-obvious. It still doesn't cover failure modes or whether duplicate leave on the same job is rejected.

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?

Four tight sentences, front-loaded with the 'WRITE:' signal, then scope, then side effects, then the prerequisite lookup and endpoint. Nothing is repeated and nothing is wasted.

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 non-idempotent write with no output schema, the description covers the operation, the side effects, the prerequisite reference lookup, and the follow-up finalisation step. Remaining gaps are minor: no indication of what identifier the call returns or how to subsequently finalise the leave.

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 83%, so the schema already carries most parameter meaning. The description contributes one useful pointer, that leave_type_id values come from list_reference_data extended_leave_types, but says nothing about fte semantics during leave or the id-vs-name precedence beyond what the schema already states.

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?

Opens with an explicit 'WRITE: record extended leave' and names the concrete leave categories (parental, long service, unpaid) plus the target resource ('an existing job'). No sibling tool does anything similar, and the POST endpoint removes any ambiguity about the operation.

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?

Gives real routing guidance by pointing to 'list_reference_data kind extended_leave_types' to resolve leave types before calling, and implies the leave must attach to an existing job (so get_job/list_jobs precedes it). It does not state exclusions, e.g. how this differs from other leave or person-update flows, so it stops short of a 5.

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