Send Friend Request

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

Goes well beyond the annotations by disclosing atomicity ('creates both pending request records and an ordinary recipient Inbox notice atomically'), crossed-request semantics, the no-auto-retry policy, and the idempotency guarantee in concrete terms. It also specifies the exact return payload and cache-replacement duty, plus per-status error handling (409, 404, INBOX_FULL, 401, 403, 429).

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?

Front-loaded with purpose and use/not-for guidance, which is good, but the body is a dense, largely unstructured block covering side effects, returns, and an extensive error catalogue. Some content is redundant — the no-automatic-retry rule appears both in 'Not for' and again in 'Side effects' — and the volume makes key constraints harder to scan.

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?

There is no output schema, so the description's explicit enumeration of the returned snapshot fields and the instruction to replace the matching host/project/player cache are necessary and present. Error behavior, auth requirements, capacity rejection, and rate limiting are all covered for a state-mutating social action.

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 the baseline is 3; the description earns an extra point by explaining where sessionToken comes from (horizon_signin_email / horizon_signin_anonymous accessToken), that userId must be the signed-in player, and that expectedRevision is a reviewed snapshot revision that must never be silently substituted. targetUserId is not discussed in the description beyond what the schema says.

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 first sentence states a specific verb+resource (sends a friend request) and qualifies it with the required precondition (reviewed player revision). It is clearly separable from horizon_accept_friend_request, horizon_decline_friend_request, horizon_cancel_friend_request and horizon_block_player in the sibling list.

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 'Use when' (player explicitly requests the action) and 'Not for' clauses (no automatic retries after timeout, no automatic acceptance of crossed requests, no changing expectedRevision without reconciling intent). It also names the sign-in siblings that must be used to obtain sessionToken, so routing is unambiguous.

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