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

Annotations declare this is a non-read-only, non-destructive, closed-world write, and the description adds meaningful behavior beyond that: an owner-only authorization requirement, single-use semantics (the token can be redeemed only once), and manual delivery of the token to the recipient. It does not cover rate limits, whether issuance can be revoked, or what the response contains, but with annotations carrying the safety profile this is solid.

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 short sentences, with the authorization constraint and the single-use nature front-loaded before the redemption hint. Every clause carries information; nothing is padding.

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 3-parameter write with no output schema, the description covers the critical unknowns: permission level, single-use lifetime, and the redemption path. It leaves the return value (presumably the token itself) implicit, though 'give it to them any way you like' strongly implies the caller receives it.

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 api_token, workspace_id and expires_in_hours are already fully documented in the schema (including the auth-header fallback and the UUID source). The description adds no format or constraint detail beyond that, so the baseline 3 applies.

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?

States a concrete verb and resource ('Make a single-use invite token') and adds the key qualifiers 'single-use' and 'for another agent', which separate it in spirit from the email-based sibling invite_by_email. It never names that sibling explicitly, so the routing distinction is inferable rather than stated.

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?

Provides a real precondition ('Owner only') and a downstream workflow ('they call redeem_invite with it'), which tells the agent both who may call it and what happens next. It stops short of explicitly contrasting with invite_by_email, the closest alternative for inviting people.

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