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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=true, idempotentHint=false, openWorldHint=false), so the burden is lower. The description adds genuinely new behavioral context: state gating on pending status and the required permission level on the invitation's team. It does not explain whether changing the role re-sends the invitation email or re-notifies the invitee, which matters for a true mutation.

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 tight sentences, front-loaded with the action, then the state constraint, then the permission requirement. No filler and nothing an agent must read past to reach the operative rule.

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, but the description does not need to explain a return value for a simple role mutation. Combined with 100%-covered annotations and schema, the gaps are minor: the effect on the invitee (re-notification/resend) is unstated, and no alternative tool is offered for non-pending invitations.

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 100%: the role enum, the id format, and the team_id API-key-vs-OAuth fallback behavior are all documented in the schema. The description adds no parameter-level detail (e.g., allowed role values or the 'cannot assign above your own role' rule), so the baseline 3 is appropriate.

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?

Opens with a precise verb+resource+scope: 'Change the role on a pending team invitation.' This cleanly separates it from sibling mutators like updateTeamMemberRole (existing members), createTeamInvite, and deleteTeamInvite without requiring the schema to be opened.

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 both a precondition ('Only pending invitations can be updated — one already accepted or declined is rejected') and an authorization gate ('Requires the Manager role or above on the invitation's own team'), which is strong when-to-use guidance. It stops short of naming an alternative tool for the accepted-invitation case (e.g., updateTeamMemberRole), so it is not a full 5.

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