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

Annotations already declare destructiveHint=true and idempotentHint=false, but the description adds substantial context the annotations cannot: the invitee receives the link by email and it is never returned, authorization scope, idempotent-looking re-invite behavior, and the two-step summary/confirmToken flow. This is exactly the destructive-operation detail an agent needs before calling twice.

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 core action and the non-returned-link caveat, then layered with permission, re-invite, domain, and confirmation facts. Dense but every clause carries information; no filler sentences.

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?

With no output schema, the description compensates by describing what a call returns (a summary and confirmToken, not the invitation link) and how to complete the operation. For a destructive, two-phase tool this is complete enough to call correctly.

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 75% and the description still adds value: it explains the emailDomain restriction semantics and, crucially, the confirmToken handshake (omit on first call, pass on second) beyond the schema wording. Minor gap: the 'email' parameter gets no additional explanation, though its format is self-evident.

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 ('Emails an invitation to work on this site') and disambiguates from nearby siblings like resend_invite and revoke_invite by noting re-inviting resends the same invitation. An agent can identify the action without opening the 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?

Gives clear preconditions ('Anyone on the site team can invite') and the re-invite behavior, which implicitly tells the agent not to reach for resend_invite. It stops short of explicitly naming alternatives or stating when not to use this tool.

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