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

Annotations only declare the generic write profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false). The description adds non-obvious behavior the annotations cannot convey: that accept creates an anonymous conversation, that decline is silent, that the policy setting changes the outcome, and the fallback link behavior. It stops short of covering auth requirements for relaying on someone's behalf or what the response contains.

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?

Three dense sentences, front-loaded with the action and its outcomes before the conditional policy detail. The middle sentence is slightly tangled but every clause carries operative information; nothing is padding.

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 state-changing tool with annotations covering safety and an output schema covering returns, the description supplies the missing pieces: side effects of each decision and the policy gate. The main omission is the provenance/semantics of knockId, which matters for correct invocation.

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 only 33% – only 'reason' is documented in the schema. The description does usefully explain the semantics of each 'decision' enum value and when each is allowed, which is value beyond the bare enum. However, knockId (a required identifier) is left unexplained, including where the agent should obtain it, so the gap is only partially compensated.

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 (respond/answer) and resource (a knock) and enumerates the four possible decisions with a short gloss on each (accept opens an anonymous conversation, decline is silent), so an agent knows exactly what the call does. It does not explicitly name the siblings it is distinct from (knock, list_knocks, answer_follow_request), so it falls short of the 5 bar.

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 real conditional guidance: accept/decline on the person's own behalf requires their 'anonymous conversations' policy to be 'send', otherwise the result is a link to forward; block/report are always permitted when the person wants it or the knock is clearly abusive. These are preconditions rather than an explicit alternative-tool routing, so 4 rather than 5.

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