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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description adds value beyond that: it specifies the concrete consequence (item no longer appears in search) and the retention semantics ('its history is kept'), which softens the destructive flag in a way annotations alone cannot communicate. It doesn't mention permissions or whether retirement can be reversed through another tool.

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?

A single sentence leads with the action and its effect, then appends the confirmation caveat. Every clause earns its place: what it does, why it matters for search, what is preserved, and what the agent must do first.

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 two-parameter mutation tool with no output schema, the description covers the effect, the data-retention outcome, and the required confirmation step. Only minor gaps remain — no mention of return value or of what an agent should do if the owner is unavailable.

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 id and reason are documented, including where to obtain the id ('from remember or search_knowledge'). The description adds no additional meaning about these parameters, so the baseline of 3 applies.

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 ('Retire a knowledge item') and adds the observable effect: search stops returning it. It is distinguishable from get_knowledge/search_knowledge by the destructive framing, but it never names update_knowledge, so the boundary between 'retire' and 'correct in place' is left to the agent to infer.

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 a clear trigger ('wrong or out of date') and a prerequisite ('Confirm with your owner before retiring it'), which is real when-to-use guidance. It stops short of naming the alternative action for items that only need amendment, so the choice against update_knowledge is implied rather than stated.

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