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

Annotations only declare readOnlyHint=false and destructiveHint=true; the description adds the full behavioral picture: two-step preview/confirm gating, single-use short-lived tokens bound to resolved people and beta lifecycle state, no emails in DRAFT, refusal on finished/archived betas, server-side dedupe returning 'alreadyTester'/'invited' without re-emailing, undeliverable handling, and custom template usage. This is far more than the annotations convey.

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 two-step procedure is front-loaded and nearly every clause carries load-bearing detail (token binding, dedupe outcomes, DRAFT suppression). It is dense and long, with several long run-on sentences and parentheticals that could be split for readability, but little is genuinely redundant.

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 4-parameter mutation with no output schema, the description covers preconditions, the confirmation handshake, per-person result states (alreadyTester, invited, emailDelivery 'undeliverable'), and downstream follow-ups (pingTesters, cancelInvitations, listPendingInvitations). Nothing an agent needs to call it correctly is missing.

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 already 100%, but the description adds meaning the schema does not: userIds and invitees 'combine freely' with at least one required (a union constraint not expressible in the schema), why userIds exist (tester emails are never exposed), and how confirmationToken interacts with identical arguments on the second call.

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 and resource ('Invites people to join this beta project as testers') and distinguishes itself from nearby siblings by naming inviteApplicants-adjacent tools (pingTesters, cancelInvitations, listOrganizationTesters). An agent can tell exactly which operation this performs without opening the 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?

Explicitly prescribes the call sequence (call without confirmationToken first, show preview, get user approval, then re-call with the token) and routes agents to alternatives by condition: use userIds for existing workspace testers from listOrganizationTesters, pingTesters to re-send pending invitations, cancelInvitations for undeliverable ones. It also states when the tool refuses (finished/archived) and when emails are suppressed (DRAFT state).

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