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

Annotations already flag readOnlyHint=false and idempotentHint=false; the description earns credit for disclosing beyond that: the mutation extends expiry by exactly seven days, and the call may be gated by organization-configurable MCP approvals plus mandatory business workflow approvals. It stops short of 5 because it doesn't say what happens to non-pending or expired invitations, or whether the send can fail/rate-limit.

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 sentences, front-loaded with the action and its state effect, with no filler. The trailing approval sentence is slightly vague ('configurable by the organization administrator') but is the only place approval gating is disclosed, so it earns its place.

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?

An output schema exists, so return values need not be described. For a single-param mutation, the description covers the effect (expiry extension) and the approval caveat, which are the two things an agent most needs. Missing only edge-case behavior for non-pending invitations and the source of the invitation ID.

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?

One parameter with 0% schema description coverage, though the schema does supply a strict UUID format and pattern. The description indirectly constrains it by saying the invitation must be 'pending', which is useful meaning beyond the schema, but never references invitationId or explains where to obtain it.

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 (resend) plus resource (team invitation email) and the concrete side effect (extends expiry by seven days), plus a qualifier ('pending') that constrains scope. It does not name or differentiate from siblings such as revoke_team_invitation, invite_team_member, or list_team_invitations, so it stops short of a 5.

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?

The word 'pending' implies this only applies to invitations that haven't been accepted/revoked, but no explicit when/when-not statement or alternative ('use invite_team_member for new invitations, revoke_team_invitation to cancel') is given. The approval note hints at a gating condition an agent should expect, which is implied usage rather than clear guidance.

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