Invite a member

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

Annotations cover only the generic safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=true). The description adds substantial context beyond that: an invitation email is sent, duplicates silently create nothing (and report that), a confirmationToken must be obtained via preview_operation with a human-approval gate, and specific auth/role requirements apply.

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?

Three tightly packed sentences, front-loaded with purpose and role options before the confirmation-token procedure and permission requirements. Every sentence carries operational content, though the security/permission clauses could be trimmed slightly.

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?

No output schema exists, and the description handles that by noting what happens in the duplicate case ('creates nothing and says so'). Combined with the permission requirements and the mandatory preview/confirmation flow, an agent has what it needs to invoke correctly; only the return payload shape is unstated.

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 description coverage is only 20% (requestId is the sole documented property), so the description must carry the load. It does: it explains email, enumerates the role enum values, explains the origin and purpose of confirmationToken, and identifies organizationId as scoped to the organization. It does not clarify the organizationId format or the requestId retry semantics beyond what the schema states, but coverage of the five parameters is strong.

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 and resource ('Invite someone to the organization by email with a role'), names the allowed role values, and describes the acceptance flow and the duplicate-address no-op case. An agent can distinguish this from list_members, update_member, and cancel_invitation without opening any schema.

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 prescribes the precondition workflow: call preview_operation with tool "invite_member" and these arguments, show the plan to the user, and call this tool only after explicit agreement. It also states the required permission (organization:manage) and role (owner), and notes the duplicate-address case where nothing is created.

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