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

Annotations already flag this as destructive and non-idempotent, and the description goes well beyond them: the recipient is not notified, no further mail is sent, and the day's twenty-request allowance is NOT restored. The quota consequence is exactly the kind of non-obvious side effect an agent needs before calling a destructive 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?

Three tight sentences, front-loaded with the action and followed by side effects and the invocation rule. Minor redundancy in the explanation of request counting, but every sentence carries 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?

For a destructive one-parameter tool with no output schema, it covers side effects, quota cost, and consent requirements well. It does not say what happens if the precondition fails (e.g., the request was already accepted) or what the tool returns, leaving a small 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 100% and the single 'contact' parameter is already documented as an email address or a name as shown by list_contacts. The description adds no further detail on identifier format or disambiguation, so the schema does all the work and baseline 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 ('take back') and resource ('a contact request the user sent'), plus a scope condition (only while unanswered). This is clearly distinguishable from siblings such as invite_contact, accept_contact, and block_contact without opening any 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?

Gives an explicit invocation constraint — 'Call it only when the user asks for it in their own message' — and a state precondition (the other person has not answered). It does not contrast with alternatives like block_contact or explain what to do if the request was already accepted, so it stops short of a full 5.

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