remove group member

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

Goes well beyond the annotations: states the role hierarchy that governs who can be removed, that no automatic retry is performed, that a same-revision replay cannot create a second effect (concrete idempotency semantics), that INBOX_FULL rolls back the whole action, and that returned groups data is the actor's snapshot only. Auth provenance (signin accessToken as sessionToken) and 401/403/429 semantics are all disclosed without contradicting readOnly=false, destructive=true, idempotent=true.

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?

Well structured with labeled clauses (Use when / Not for / Requires / Side effects / Returns / Errors) and front-loaded routing information, but roughly 350 words for a five-parameter call. The error block repeats generic account-level guidance (HORIZON_API_KEY wrongness, per-minute rate limiting) that applies to every tool in the family rather than to this one.

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, revision-guarded mutation with no output schema, the description covers auth, authorization, rollback, idempotency, return shape and the 409/401/403/429 error paths, which is close to complete. The dangling requestId reference is the one inconsistency an agent could trip over.

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, but the description adds real meaning: sessionToken comes from horizon_signin_email/anonymous's accessToken, and expectedRevision is the 'reviewed' revision that must never be refreshed and replayed after an uncertain response. One gap: it refers to 'the exact pending requestId where applicable' although no requestId parameter exists in the schema, which could confuse the agent.

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 verb+resource ('remove group member') is unambiguous, and the side-effects line distinguishes the two authority cases (leader removes officer/member; officer removes only member), which separates it from horizon_leave_group (self-leave) and horizon_set_group_member_role. The opening sentence, however, largely restates the tool name ('Applies the explicit remove group member action'), so the differentiation arrives later than it should.

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 confirms this group action) and 'Not for' clauses (replacing reviewed revisions/request IDs, bypassing a leader's block, automatic retry) set hard boundaries. It also names the reconciliation alternatives, horizon_get_groups and horizon_get_group_pending, for the conflict path, leaving nothing to inference.

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