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

Annotations only carry openWorldHint, so the description must do the behavioral work, and it does add real value: the auto-add vs pending-invite asymmetry is a non-obvious side effect, and 'Needs an account-wide key' discloses an auth prerequisite. It stops short of covering failure modes (already-invited email, invalid domain) or whether the invite is reversible.

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 are well front-loaded with the core action and outcome branches, but the trailing '[#d3c424]' artifact is noise that should not be in a tool description, and the '(agency / Enterprise)' aside reads as leftover annotation rather than usable information.

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?

For a 4-parameter mutation with no output schema and only openWorldHint annotation, the description covers the key things an agent needs: what it does, the two possible postconditions, and the credential scope. Remaining gaps (idempotency, duplicate-invite behavior, what the response returns) are modest.

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%, so email, role, account_role, and workspace_uuid are all documented in the schema and the baseline is 3. The description echoes role/workspace pre-assignment but adds no syntax, defaults, or enum meaning beyond the schema; the '(agency / Enterprise)' parenthetical is ambiguous and does not map cleanly to any parameter.

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?

Specific verb (invite) + resource (someone to the account) with a clearly scoped optional extension (pre-assign workspace + role). It is distinguishable from siblings like assign_workspace_member, accept_invite, and resend_invite, which handle adjacent but different lifecycle steps.

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 description explains the two outcome branches ('existing user is auto-added immediately; a new email gets a pending invite') and the credential requirement, which tells the agent what to expect. However, it never names sibling alternatives such as assign_workspace_member (for members already in the account) or revoke/resend_invite, so the routing guidance is implicit rather than explicit.

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