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

With no annotations, the description carries the full burden and does so: it discloses that this is a mutation requiring user confirmation, that a side effect is an email with an acceptance link, and that the result's mail_sent flag is the source of truth for whether that side effect occurred. It goes further to prescribe exactly what the agent should say in both the true and false cases, including the recovery path (admin resend or copy 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?

It is front-loaded with purpose and scope, then constraints, then outcome handling, and every sentence carries an operational instruction (don't pass org id, role ceiling, mail_sent wording rules). No filler or restatement of the title.

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?

There is no output schema, so the description supplies the one return value that matters (mail_sent) and how to report both outcomes. Combined with the schema's idempotency_key, an agent has everything needed to call this correctly and to narrate the result accurately.

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 100%, so the baseline is 3; the description nonetheless adds value by reinforcing the role privilege constraint and by clarifying that no organization parameter exists or should be supplied, which is a common source of wrong calls. It does not add anything about email or idempotency_key semantics beyond the schema.

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 opening sentence gives a specific verb (invite) and resource (a person, by email, at a role) plus the implicit scope of 'your organization'. It is clearly distinguishable from siblings like change_user_role, cancel_invite, or resend_invite, which deal with existing users or existing invitations.

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 states the precondition (the organization is fixed by context - never pass an organization id) and the privilege ceiling on roles. It also mentions that an admin can resend a failed email, which points at resend_invite without naming it explicitly, and gives no explicit exclusion for cancel_invite or change_user_role. The usage context is clear but not full sibling routing.

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