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

Adds side-effect detail the annotations cannot express: the invitee gets a new link valid 7 more days and the old link stops working. This explains the non-idempotentHint and non-destructiveHint in concrete terms and warns of the pending-state requirement. It does not cover permissions or what the call returns, but the key mutating consequence is disclosed.

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?

Two tight sentences, front-loaded with the essence and then the constraint. The opening line duplicates the title verbatim, which is the only wasted space, but the rest earns its place with no filler.

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 and a single UUID input, an agent needs only the precondition, the side effect, and the failure mode — all present. The only gap is the response shape (does it return the refreshed invitation?), which is minor for such a narrow operation.

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 the single parameter is already fully documented in the schema, including the 404 not_found case for another company's invitation. The description contributes only the pending-state error condition, which is state rather than parameter meaning; baseline 3 is appropriate when the schema carries the semantics.

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?

Names a specific action (re-sending an invitation) and immediately clarifies what 'again' means: a new email with a new link. This distinguishes it in spirit from invite_member (create new) and cancel_invitation (invalidate), though no sibling is named explicitly, so differentiation is inferred rather than stated.

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 a concrete precondition — 'Only an open invitation can be sent again' — with the exact failure code (422 invitation_not_pending), which is real usage guidance. It does not name the alternatives (invite_member, cancel_invitation) or when to prefer re-sending over cancel+re-invite, so it stops short of full routing guidance.

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