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

No annotations are provided, so the description carries the full burden. It mentions 'best candidate plus ranked alternatives' but does not explain what determines 'best' or how the ranking works. It also does not disclose whether this is a read-only operation (likely) or any side effects, leaving significant behavioral ambiguity.

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 composed of two succinct sentences that front-load the key information. Every word adds value, and there is no redundancy or unnecessary 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?

Given the low complexity (one parameter, no output schema), the description is fairly complete. It explains what the tool returns and when to use an alternative. However, it could be more complete by clarifying the output format or how to interpret 'ranked alternatives.'

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 provides a full description for the only parameter (message_id: 'Message id (uuid) from list_messages or wait_for_message.'). The tool description adds no additional meaning beyond this, so the baseline score of 3 is appropriate.

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 clearly states 'OTP/verification code extracted from one message: best candidate plus ranked alternatives.' It specifies the resource (OTP from a message) and the action (extract), and hints at the output format with 'best candidate plus ranked alternatives,' distinguishing it from sibling tools like get_message.

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 explicitly tells when not to use this tool: 'If you are still waiting for the email, prefer wait_for_otp.' This provides clear guidance on choosing between siblings, and the context is directly actionable for an AI agent.

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