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

The description carries genuinely useful behavior beyond the annotations: invocation is a no-op preview, it returns a change preview and a confirmation link, and only the merchant on that page can finalize. This is consistent with readOnlyHint=false and idempotentHint=false, since each call evidently mints a new preview token rather than performing the invite. It stops short of describing what the preview contains or any rate limiting/expiry on the confirmation link.

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?

The preview/confirmation caveat is front-loaded right where it matters and the whole thing is four short sentences. However, the money-format sentence is dead weight for a tool whose only parameter is an email address, and it dilutes an otherwise tight definition.

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 one-parameter tool with annotations and no output schema, the description supplies the critical missing context: that the call is safe because it only previews, what it returns, and who must confirm. Only the exact shape of the preview and the invite lifecycle after acceptance are left implicit.

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 the email parameter already documents the 7-day accept link and the Staff role scope. The description adds no meaning to that single parameter, and its one concrete detail ('Money is integer minor units (cents)') does not apply to this tool at all, so a 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?

The first sentence states a specific verb and resource ('Invite someone to help run the shop'), and the following sentences immediately qualify that the call itself produces only a preview plus a confirmation link. That qualification is essential because the tool name implies the invitation is sent. No sibling tool in the list covers staff invitation, so there is nothing to differentiate against, which keeps this just short of 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?

Scope ('help run the shop') and the completion path ('Only the merchant, on that page, can make it happen') imply when to use it, but there is no explicit when-not-to-use or a named alternative. The distinction that Admins are invited via Settings rather than this tool appears only in the input schema, not in the description, so an agent scanning descriptions alone would not see the exclusion.

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