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

Annotations only declare the safety profile (not read-only, not destructive, not idempotent); the description adds the full lifecycle: the friend's assistant surfaces it, they accept/decline/ask a question, unanswered requests expire after 14 days, and it is not a grant of permission. It also explains the dedup contract for retries.

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?

Dense but front-loaded: the core action and gating condition come first, then lifecycle, then the idempotency rule. Slightly long, but each sentence conveys a distinct behavioral fact rather than restating the name.

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 an 8-parameter mutation tool with no output schema, the description covers the missing pieces an agent needs: recipient constraints, source-of-content rules, expiry, response lifecycle, and retry safety. Nothing material is left unstated.

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%, so baseline is 3, but the description adds real meaning for the core fields — 'what' must be in the person's own words, 'to' must be a friend — and clarifies the retry semantics of client_key beyond the schema's wording. It is silent on links/summary/deadline/time_zone, so not a 5.

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 ('Send a friend a request') plus the payload semantics ('one clear thing your person is asking them for'), with a concrete example. An agent can distinguish this from sibling answer_friend_request / my_requests without opening a 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?

Explicit gating conditions: 'Only when your person asks you to, in their words' and 'Friends only (see my_friends)', routing to the sibling that enumerates valid recipients. It also states the follow-up path (my_requests), covering when to use vs. inspect.

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