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

Annotations already declare this as a non-read-only, open-world, non-destructive action; the description adds real substance beyond that by explaining the authentication model (the invitee signs in with their own email), the billing model (hosting stays with the owner), and the retained owner-only powers. It does not say whether the invite is sent immediately, what happens if the email already has access, or whether repeat calls are idempotent.

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 tight sentences with no filler, and the core capability comes first followed by the constraint context. The opening is slightly oblique because it describes the outcome rather than naming the act of inviting.

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 simple two-parameter, non-destructive mutation with no output schema, the description covers the important agent-facing concerns: who gets access, how they authenticate, who pays, and what the owner alone controls. Only edge-case behavior (duplicate invitations, delivery of the invite, failure modes) is left uncovered.

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 50%: the `site` parameter is documented as slug or id, but `email` has only type and maxLength. The description partly compensates by making clear the email is the invitee's own sign-in identity rather than a notification address, which is meaningful added meaning, though format or account-existence requirements remain unstated.

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 states the concrete effect of the tool — granting another person the ability to edit and publish the site — which is more informative than the name alone and clearly separates it from visitor-oriented siblings like invite_visitor. It never uses the word "invite" and never names the action as adding a member, so the mapping from tool name to effect requires a small inference.

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 intended use (give someone editorial access to this site) is implied clearly, but there is no explicit when-not guidance and no named alternative such as invite_visitor or list_members for checking existing access. The permission boundary sentence helps the agent reason about scope but is not framed as usage guidance.

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