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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: exact auth header, required scope, the caller's role constraint, rejection of OAuth tokens and other keys, and the specific 403 failure mode for unclaimed sandbox workspaces. That is the kind of failure-path detail an agent needs before calling.

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 sentences, front-loaded with purpose, then auth, then workspace precondition. Dense but no filler; 'a token or any other key is refused' borders on redundant with the preceding scope statement but usefully rules out the OAuth path.

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?

There is no output schema, yet the description names the returned fields (email, role, sent timestamp) and covers both auth and workspace-state preconditions that produce distinct error codes. Nothing material for a correct call is left out.

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?

The tool takes zero parameters, so the baseline is 4; the description correctly implies no filtering or pagination inputs are needed and instead spends its words on auth and response fields.

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?

The opening clause names a specific verb and resource and narrows scope to invitations 'still waiting to be accepted', which cleanly separates it from list_team_members (accepted members) and revoke_invitation (mutation). It also enumerates the returned fields, so an agent knows exactly what it gets.

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?

Prerequisites are stated with unusual precision: x-api-key with team:admin scope, held by a current owner/admin, and a claimed workspace or a 403. What's missing is an explicit alternative ('for accepted members use list_team_members'), so the when-to-use signal is implied by the resource scope rather than named.

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