leave group

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

The annotations already declare a destructive, idempotent, open-world write, but the description adds what they cannot: a leader must transfer ownership first unless they are the sole member, no automatic retry is allowed, and a clean replay of the same revision cannot create a second effect. It also explains error codes, including the 409 conflict and the INBOX_FULL rollback.

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 well front-loaded with Use when / Not for / Requires / Side effects / Returns / Errors labels, so the agent can scan each section quickly. The Errors paragraph is dense and long, but each sentence still carries operational value for a destructive call.

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 must carry the return values, and it does: it defines the {groups, group} shape, tells the agent that group is null after leaving, and explains that groups is the actor's full snapshot rather than the target's private state. Since this is a destructive, idempotent write, the description also covers auth setup, key handling and rate limits.

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 schema already documents all four parameters, which sets the baseline at 3. The description still adds useful meaning: sessionToken must come from a horizon_signin_* accessToken, expectedRevision is the exact reviewed revision that must not be silently refreshed, and the pending requestId carries the original decision identity.

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 opens with a specific verb and resource: 'Applies the explicit leave group action using the reviewed group revision.' This distinguishes it from siblings like horizon_remove_group_member or horizon_delete_group, though it never names those alternatives directly.

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 gives explicit 'Use when' and 'Not for' clauses and names concrete exclusions: it must not replace reviewed revisions or request IDs, bypass a leader's block, or retry automatically. It also routes the agent to horizon_get_groups and horizon_get_group_pending for reconciliation.

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