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

Annotations already declare the write, non-idempotent, non-destructive, closed-world profile. The description adds genuinely new behavior: the response contains the raw single-use accept token — a security-relevant detail the annotations do not expose — and it discloses the pairing with accept_invitation. It omits permission requirements beyond the implied admin actor.

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; the behavioral fact (invite + token) is front-loaded and the lifecycle hint follows. Nothing is redundant, though the second clause is only a pointer rather than added substance.

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?

An output schema exists so the return payload need not be re-explained, and annotations cover the safety profile. But for a nested-body mutation with 0% schema coverage, the description leaves tenant_id and billing_contact semantics and the required authorization parameter entirely to inference, which is a real gap for correct invocation.

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 0% for a 3-parameter nested body, so the description carries the full burden and mostly does not. It conveys that an email address and an access level are supplied, but says nothing about tenant_id (presumably defaulted to the caller's tenant), the billing_contact flag, or valid level values.

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 specific verb (invite/create), the resource (invitation), the target (an email address in the caller's tenant) and the access-level scope, plus what is returned. It distinguishes itself from list_invitations, revoke_invitation and accept_invitation by naming the accept-side counterpart, so an agent can place it in the invitation lifecycle without opening a schema.

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?

"Call this when a tenant admin wants to add a new member" gives a clear triggering condition and an actor, and it routes the agent to `accept_invitation` for the next step. It stops short of stating when not to use it (e.g., when a member already exists), so it is not a full when/when-not rule.

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