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

Annotations only declare the generic profile (not read-only, open-world, non-idempotent, non-destructive); the description adds substantial context: authorization requires an active owner/admin principal, the code is returned once and stored only as a hash, the invite is a bearer token, expiry/revocation behavior, and that the caller gains no privileges. Strong disclosure, though the email-delivery and expiry details largely restate the schema.

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?

Front-loads purpose and authorization, then walks through the two-pass call pattern in a logical order with the highest-stakes warning in caps. It is dense and long, and some sentences are redundant (the repeated 'never go hunting for an address' instruction) or add noise (the RTSC ticket references), which keeps it from a 5.

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?

With no output schema, the description fully carries the burden: it explains what the no-argument call returns (the questions as data with exact options), what the final call returns (the raw code, once), the authorization preconditions, and the reversibility/expiry model. An agent has everything needed to invoke it correctly end to end.

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 earns more by explaining the intent behind choices the schema can't convey — that omitting `projectIds` is the safe default granting only this folder's project, why `allProjects` conflicts with it, and when `inviteeUserId` should be used. It doesn't enumerate formats or defaults beyond the schema, but the decision semantics are genuinely additive.

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 ('Invite a PERSON into your org') with explicit on-behalf-of scoping, and distinguishes it from siblings like list_invites, revoke_invite, and accept_invite by describing minting an invite code versus managing one. An agent can identify this as the creation/issuance step 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?

Gives explicit when-to-use rules ('NEVER call this unprompted — your human names the person'), a mandatory workflow ('CALL IT WITH NO ARGUMENTS FIRST'), and precise selection criteria between `projectIds`, omitting it, and `allProjects: true`. It even names the failure mode of combining the two. This is about as complete as usage guidance gets.

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