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

Adds real context beyond the annotations: it explicitly negates side effects ('No files, tenant invitations or financial changes') and warns that the call 'creates once and is never retried automatically', which explains the non-idempotent semantics rather than merely restating idempotentHint=false. It does not describe the response payload or what a duplicate submission would produce, keeping it just below full marks.

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 the write semantics and the action, followed by the endpoint and the side-effect boundary. Nothing is repeated from the schema or annotations, and every clause adds information.

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 mutation with no output schema, the description covers confirmation, side-effect scope, and retry behavior well. However, with 10 parameters at low schema coverage and no return-value hints (no task id returned?), an agent still lacks the field-level guidance needed to construct a complete call.

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 only 30% across 10 parameters, so the description needed to carry weight here, yet it mentions only 'unit and task details' generically. Undocumented fields such as task_type, emergency, private, tags, api_notes, due_date/due_time, and assigned_managers get no meaning, format, or default guidance from either source.

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 ('create a maintenance task associated with a unit') and even names the endpoint shape POST /v2/units/{unit_id}/tasks, which makes the required unit_id immediately obvious. The 'WRITE:' prefix disambiguates it from the read-oriented siblings (get_task, list_tasks) in the surrounding tool set.

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 an explicit trigger ('when the user requests it') and a prerequisite step: 'Confirm the intended unit and task details first', which is genuinely actionable pre-call guidance. It stops short of naming an alternative for cases like appending commentary to an existing task (arthur_add_task_note), so the routing guidance is clear but not exhaustive.

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