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

No annotations are present, so the description carries the full burden. It explicitly warns 'Sensitive' and explains the consequence: 'invalidates a machine authentication token.' It also discloses the return value ('Returns the revoked M2M token') and default connection behavior, giving a clear behavioral picture.

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 description is compact and front-loaded: purpose, warning, usage flow, return, and cost are each covered in short sentences. There is no filler or redundant detail.

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 destructive revoke tool with no annotations, the description covers purpose, side effects, usage flow, and return value. The output schema handles return format details. The only minor omission is explicit mention of irreversibility, but 'invalidates' already implies it.

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 input schema already describes both parameters with 100% coverage, including prefixes and default behavior. The description's parameter-related guidance ('Call clerk.get_connected_accounts first', 'Pass clerk_instance_id... or omit') largely restates schema content, adding only a sequential prerequisite.

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 'Revoke an M2M token by id in a connected Clerk instance,' using a specific verb and resource. The 'Sensitive' callout and 'invalidates a machine authentication token' further clarify the action, and the structure distinguishes it from other revoke_* siblings by targeting M2M tokens.

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 'Call clerk.get_connected_accounts first' and explains the two modes for targeting a connection ('Pass clerk_instance_id to target a specific connection, or omit it to use the default account'). This provides clear context on how to use the tool, though it doesn't explicitly describe exclusions or alternatives.

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