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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, and the description adds substantial behavioral context beyond that: it deactivates linked reviewer agents, strips the ICP from content pipelines, archives rather than permanently deletes, and is not tool-recoverable. It also discloses the sensitive-tier approval behavior. This is exactly the kind of side-effect disclosure an agent needs for a destructive operation.

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?

The description is dense but well-organized: the core behavior and side effects come first, then routing/confirmation, then approval details. Every sentence carries operational information. It is slightly long due to the approval-tier explanation, but that content is necessary for correct invocation and is clearly separated.

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, non-recoverable operation with no output schema, the description covers everything an agent needs: what the tool does, what side effects occur, how to get the required ID, when to confirm with the user, and how the approval flow behaves. The only minor gap is that it doesn't describe the return value, but for a delete/archive operation that is not critical.

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 100%, so the schema already documents all three parameters. The description adds value by explaining that icp_id comes from get_icps and that companyId is a company-scoped membership requirement. The reason parameter is optional and self-explanatory, so the description doesn't need to elaborate further.

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 opens with a specific verb and resource ('Delete a saved Ideal Customer Profile (ICP)') and immediately distinguishes the operation from a permanent delete by stating it archives rather than removes. It also names the sibling get_icps for ID retrieval, which helps disambiguate from update_icp and create_icp.

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?

The description gives explicit when-to-use trigger phrases ('delete this ICP', 'remove this customer profile', 'get rid of this persona'), a required precondition (call get_icps first for icp_id), and a mandatory confirmation step before calling. It also explains the routing and approval flow, leaving no ambiguity about when this tool should be invoked.

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