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

Annotations already declare readOnly=false, destructive=true, idempotent=false and openWorld=true, and the description reinforces the write/idempotency profile rather than contradicting it. It adds genuinely new behavioral context: the confirm:true gate and that "CATS may notify the assignee" — a side effect an agent cannot infer from annotations or schema.

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 tight sentences with the safety gate front-loaded ("WRITE: Requires confirm:true") before the operation itself. Every clause carries information — idempotency, notification side effect, endpoint — with 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?

For a 7-parameter mutation with no output schema, the description covers the precondition, side effects and retry semantics well. The remaining gap is return behavior — nothing says what the caller gets back (e.g. the new task id) to chain into cats_get_task — which matters with no output schema to fall back on.

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 100%, so the schema already documents every parameter including the about_type enum, priority range and the about_id/about_type pairing. The description only restates the about/assignee concept at a high level, adding no syntax or format detail beyond the schema — baseline 3.

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?

Specific verb+resource ("create a task in CATS") with scope qualifiers: what it can be attached to (candidate, contact, company, job) and that it can be assigned. This clearly separates it from the read siblings cats_get_task, cats_list_tasks and cats_list_candidate_tasks.

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?

States the hard precondition "Requires confirm:true" and warns that each call creates a new task (not idempotent), which is actionable guidance against blind retries. It does not name an alternative (e.g. cats_add_candidate_activity) or say when a task is preferable to an activity log entry, so it stops short of full routing guidance.

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