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

Annotations already declare destructive=true, idempotent=true and openWorld=true, yet the description adds substantive context beyond them: the role/auth prerequisite, the state precondition, the concrete error code for unavailable invites, confirmation that repeat calls are idempotent, and the non-recallable push notification side effect. Nothing here merely restates an annotation.

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 the two constraints that matter most (login/role and purpose), then chain, then gotchas, using consistent bracketed sections. Information-dense with no filler; each sentence carries a distinct operational fact.

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 2-param mutation with no output schema, the description supplies everything an agent needs: auth, prerequisite state, workflow chain, failure mode, idempotency behavior, and external side effects. There is no material gap left for correct invocation.

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% and both fields have minimal descriptions, so the schema baseline would be 3. The description adds real value by documenting where inviteId comes from (list_organization_member_invites), turning an opaque id into a discoverable value, though it says nothing extra about organizationId.

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+resource (revoke an invite) with scope narrowed to invites that have not been responded to, and notes the consequence (recipient can no longer accept). This clearly distinguishes it from siblings like remove_organization_member (members, not invites) and respond_organization_invite (the recipient's side).

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?

Explicitly gates usage on login and OWNER/ADMIN role, prescribes the confirmation step before acting, and names the exact workflow chain (list_organization_member_invites → this tool). It also states when the tool does NOT work (accepted/declined/expired), which is exactly the when-not guidance the dimension asks for.

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