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

Annotations already declare destructive=true and idempotent=false, but the description adds important consequences: source material is unrecoverable, embeddings are removed, the agent keeps answering without the material, and citations persist until `agent_train` reruns. It also states the required "Agents" permission.

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 front-loaded with the destructive action and consequence, then gives confirmation guidance, alternatives, and permission requirements. Every sentence adds useful information without waste.

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 two-parameter tool with no output schema, the description covers consequences, user confirmation, alternatives, and permissions. Nothing essential for correct invocation is missing.

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%, and both parameters are documented in the schema with their sources (`kb_list` and `agent_list`). The description does not add meaning beyond the schema, so the baseline of 3 is appropriate.

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: remove a knowledge entry and its embeddings. It also distinguishes the tool from `kb_attach` and `kb_list`, so an agent can identify its role 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?

Explicitly says to confirm with the user first, points to `kb_list` for inspection, and names `kb_attach` as the alternative when the goal is to stop one agent using an entry without deleting it. This gives clear when-to-use and when-not-to-use guidance.

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