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

Annotations already declare destructiveHint=true, but the description adds the cascade semantics (documents and chunks removed), the returned document count, ownership scoping, and the exact two-phase protocol with status='confirmation_required', action_id and plan_token. That is real behavior beyond anything in the annotations.

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 destructive scope, which is right, but the confirmation process is stated twice — once in 'runs only after you confirm via confirm_action' and again in the CONFIRMATION sentence. The repetition costs space without adding 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?

Given one parameter, no output schema, and high-risk behavior, the description covers the cascade, ownership, and the propose-then-confirm lifecycle, including the status value to expect. It does not say what happens if the plan_token expires or is rejected, a minor gap.

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 0% and the single parameter is described only as 'by id', and the schema's integer-or-string union is not explained. The description does add the ownership constraint on which ids are reachable, which is meaningful beyond the schema.

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 (delete), resource (KB collection), and cascade scope ('AND all its documents and chunks'), plus the id key. Distinguishes it from kb_delete_doc, which removes a single document rather than a whole collection.

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?

Makes the when-to-use context explicit: only the caller's own collection, destructive, and gated behind confirm_action. It does not name a sibling alternative such as kb_delete_doc for partial removal, so the routing advice 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.