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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds real value beyond that: it discloses cascade behavior ('deletes it everywhere it is linked') and the shared-knowledge authorization constraint that yields 403 shared_with_other_agents — both materially affect invocation risk.

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?

Very short and front-loaded, with the cascade scope stated before the error rule. The leading line restates the title, a minor redundancy, but nothing else is padded.

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 2-param tool with full schema coverage and no output schema, the description covers the key gaps an agent needs: cascade scope and the authorization condition. It is largely complete, missing only explicit sibling routing.

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%; both agent_id and knowledge_base_id are documented in-schema with their 404/403 error semantics. The description adds no parameter-level detail, so the baseline 3 applies — the schema does all the work.

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) and resource (knowledge base), and the second sentence clarifies scope: it deletes the KB 'everywhere it is linked', which is more than the title conveys. It does not explicitly contrast itself with replace_knowledge_base or the other delete_* siblings, so differentiation relies on the reader inferring from the reference to the shared-knowledge rule.

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?

It alludes to an alternative operation ('the same shared-knowledge rule as replacing') and surfaces a failure condition (403 shared_with_other_agents), which implies when the delete will be refused. However, it never says when to choose delete vs replace, and gives no explicit when-not guidance, so routing is only implied.

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