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

Annotations already flag destructiveHint and idempotentHint, but the description adds what the annotations cannot: exactly what else is destroyed (notes, tasks, deal terms), that the operation is two-phase with a preview and confirmation_token, and that removed creators stay excluded from future searches. The token flow in particular is behavior an agent cannot infer from 'destructive'.

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: what it does, how the two-step confirmation works, and the lasting consequence. The destructive warning and the confirmation protocol are front-loaded where an agent will see them before acting.

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 destructive mutation with no output schema, the description covers the cascade, the confirmation protocol, and the post-removal search behavior. It does not say what the preview call returns or what auth/permissions are required, which the uid and bearer_token parameters hint at but never explain.

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 75% and the schema already describes confirmation_token, but the description reinforces the sequencing rule beyond the schema ('call again with the token only after the user confirms in a later turn'), which matters because it forces a turn boundary. lead_id, the one required parameter, has no description in either place, leaving a small gap.

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 ('Permanently remove a creator from the user's Creator CRM') and immediately scopes the blast radius with 'including its notes, tasks and deal terms'. That cascade detail is what separates it from siblings like remove_leads or untrack_creator, so an agent can discriminate without opening the 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?

Gives clear operational context: it is destructive, needs a preview + user confirmation in a later turn, and removal is persistent ('not delivered again by searches'). It never names the alternative siblings (remove_leads, untrack_creator, update_crm_lead), so there is no explicit when-not guidance, which keeps it below a 5.

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