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

Annotations only give the safety profile (destructive, idempotent, open-world); the description adds rich behavior the annotations cannot express: 7-day link validity, seat reservation, token expiry, stale_revision handling, replay semantics returning 'applied with replayed: true', and that a refused token is not consumed. It also flags CRM values as untrusted data — a genuine prompt-injection warning.

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?

Purpose is front-loaded and the confirmation protocol is broken into clear sequential instructions. It is lengthy but nearly every sentence carries operational weight; the closing line on untrusted CRM content slightly duplicates the go-ahead discussion but is defensible as a safety note.

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 mutation tool with no output schema, the description fully describes what comes back at each stage (preview summary/changes/warnings/token, replay result, stale_revision). An agent has everything it needs to call this correctly on both passes.

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 75% and the schema already documents roleId, workspaceId, and confirmationToken. The description reinforces the confirmationToken lifecycle and the need for identical arguments on the second call, adding procedural meaning beyond the schema, though it says nothing extra about email format or roleId sourcing.

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 description opens with a precise verb+resource+scope: 'Invites a person by email to join the workspace with a role.' An agent immediately knows this creates an invitation, not a member directly. It does not, however, explicitly contrast itself with close siblings such as resend_invitation or cancel_invitation, which is what would push it to 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?

It prescribes an exact two-call protocol (first without confirmationToken to preview, then with it only after explicit approval), defines what does and does not count as a go-ahead, and says to re-preview if anything changes. This is a textbook when/when-not example with no inference required.

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