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

No contradiction with annotations. It adds high-value behavior beyond readOnly/destructive/idempotent flags: no email is sent, the assistant must surface the returned invitation and wait for explicit user authorization before calling send, and membership alone grants no dossier access or business approval.

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?

Every clause is information-bearing and the most decision-critical facts (does not send, authorization required) are front-loaded. No wasted words despite covering permissions, workflow, and side effects.

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 mutation tool with no output schema, the description covers permissions, side-effect boundary, required user confirmation, and the returned fields (email, role, workspace, revision). This is sufficient to call it correctly and to know what to show the user.

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?

The description assigns meaning to role ('least required') and email ('exact') beyond the schema enum/format. IdempotencyKey semantics are already explained thoroughly in the schema; locale is left to its default/enum, so the low 25% coverage is only partly compensated.

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 action ('prepare'), resource ('workspace invitation'), and precise input policy (exact email and least required role). The phrase 'Does not send email' cleanly separates it from the sibling send_workspace_invitation, and the role list matches the schema enum.

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 says 'Owner/admin only', gives the workflow (prepare → show → get explicit authorization → call send), and conditions for not using it as a send operation. This is enough for an agent to decide between this and send_workspace_invitation.

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