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

The description discloses critical behavior beyond annotations: only the draft is queued, the actual email requires an admin action on the Send Notice screen, the greeting is auto-added, and bell=true triggers an in-app notification. It also flags admin-only usage. No contradiction with the annotations exists, and the disclosure materially changes how an agent should invoke and verify the operation.

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?

Three sentences carry all essential information with no redundancy. The most important constraint (queue-only, admin-only) is front-loaded, followed by usage context and parameter guidance. Every sentence earns its place, making the description dense yet easy to parse.

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 simple 4-parameter action with no output schema, the description covers purpose, when to use it, admin restrictions, the asynchronous send behavior, body format rules, and the optional bell flag. Nothing an agent needs to invoke it correctly is missing, and the absence of an output schema is acceptable because the operation is a fire-and-forget queue request.

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?

With 75% schema description coverage, the schema already documents user_id, body, and bell. The description adds value by clarifying body formatting ('blank line = new paragraph'), explaining the auto-added greeting, and explicitly defining bell's effect ('raises an in-app notification when sent'). It also names the undocumented subject parameter in context, partially compensating for that gap.

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 description opens with a specific verb and resource: 'Queue a one-off notice email to a user for admin review (ADMIN-ONLY).' This clearly distinguishes it from read-only account tools like account_report or account_profiles and from other stage_* staging tools, while the parenthetical 'admin-only' further narrows its audience and scope.

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?

The description states a clear trigger: 'Use after an ops-review finding that warrants proactive user outreach.' It also sets an explicit boundary by emphasizing this action only queues a draft and does not send, preventing misuse. It does not name alternative tools, but the provided context is sufficient to guide selection among many account and staging siblings.

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