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

Annotations already declare destructiveHint=true and idempotentHint=false, and the description reinforces the destructive path with 'Only delete when the user asks'. It adds genuinely non-schema behavior: the cost is free, the tool returns the updated creator, and log_touch has a state transition ('the first touch moves a sourced creator to contacted') that an agent could not infer otherwise. Auth details are left to the schema's uid/bearer_token descriptions.

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 the resource and scope, and every clause carries information — the action-to-parameter mapping, the date semantics, the side effect, and the deletion guard. It is a single dense run-on paragraph, which costs a little readability, but there is no filler to cut.

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 an 8-action, 12-parameter destructive dispatcher, the description covers scope, per-action parameters, return value, cost, and the key state transition. It leaves authentication and idempotency-retry behavior to the schema's own parameter descriptions, which is reasonable given they are documented there.

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?

With 67% schema coverage across 12 parameters, the description does real work by mapping each parameter group to its action (body/note_id for notes, title/due_at for tasks, task_id for complete/reopen/delete, channel/text for log_touch). It also adds format semantics the schema lacks: due_at accepts YYYY-MM-DD or ISO, and a bare date resolves to 09:00 UTC.

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?

The description names the resource precisely (one CRM creator's record) and enumerates the eight action values it accepts, so an agent knows exactly what operations are available. It does not, however, contrast itself with near-siblings like update_crm_lead or remove_crm_lead, so the boundary is only implicit in the action list.

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?

Usage guidance is limited to 'Only delete when the user asks' and the cost signal 'Free'. That gives a real when-not rule for the destructive path, but there is no routing guidance for choosing this tool over update_crm_lead, save_creator_to_crm, or list_crm_leads when a user asks to 'update a lead'.

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