accept_friend_invite

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, and openWorldHint=true, so the safety profile is partly covered. The description adds value beyond that: the environment write-gate flag and the candid warnings 'Not live-validated' / 'Mutation behavior has not been live-tested', which materially affect an agent's willingness to call it. It does not describe the side effects on the invite or friend relationship, so a 4 rather than 5.

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?

It is short and front-loads the endpoint, which is good. However the two warnings 'Not live-validated' and 'Mutation behavior has not been live-tested' say the same thing twice, and the telegraphic fragments make it denser than it needs to be.

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?

An output schema exists, so return values need not be explained, and the annotations cover the safety/idempotency profile. The remaining gaps are the semantics of 'query' and 'confirm_destructive' and what the accept does to the underlying invite state, which keeps it out of 5 territory.

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 0%, so the description must compensate, and it does for two of four params: it names the path key ('invite_id') and points the payload at get_schema('ConnectedFriendsInviteLinkAcceptRequestProto'). That is a useful, actionable pointer, but 'query' and especially 'confirm_destructive' are left completely unexplained for a mutation tool.

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 gives a specific verb+resource ('accept' an invite link) and maps it to a concrete endpoint (POST /v1/connected-friends/invite-links/{invite_id}/accept), so an agent can distinguish it from create_friend_invite and get_friend_invite. It doesn't explicitly name those siblings, so it falls short of a 5.

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?

It states a hard prerequisite ('requires FLIGHTY_ALLOW_WRITES=true') which is genuinely useful for invocation, but gives no guidance on when to prefer this over checking the invite with get_friend_invite first, nor any exclusions. Usage is implied by the verb rather than spelled out.

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