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

Annotations only provide generic hints (not read-only, not destructive), so the description carries the behavioral burden. It discloses meaningful traits: privacy-preserving behavior, search order, external data sources, success conditions, token lifetime, and that the street address is never returned. However, it does not clarify whether resolution has side effects such as consuming or generating a token beyond the single sentence.

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 compact and front-loaded with the key purpose, then packs search behavior, resolution conditions, and the privacy guarantee into efficient sentences. Every sentence adds substantive information without marketing fluff.

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?

With no output schema, the description should explain what the agent can expect upon success or failure. It says it resolves to a token and does not return the street address, but it does not describe token format, error cases when permission or address is missing, or whether the caller should call request_delivery_permission first. Overall adequate but with clear gaps.

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?

The input schema covers all three parameters with descriptions, so the baseline is 3. The description adds high-level context about searching and resolving but does not explain parameter relationships or priorities beyond what the schema already says, such as when to use query versus contactId.

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?

The description clearly states the tool resolves a person to a short-lived one-time delivery token and emphasizes privacy, which distinguishes it from sibling tools like send_handwritten_card and request_delivery_permission. However, the opening phrase 'way to send something to a person' slightly blurs the line between resolving and actually sending, so it is not fully precise.

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?

The description implies usage context by noting it searches OnceAsk first, can discover missing people from Google Contacts or Gmail, and requires recipient permission and a current address. It does not explicitly contrast with sibling tools or state when to choose request_delivery_permission or send_handwritten_card instead, leaving the decision partly to inference.

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