bardo_contact_delete

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

The description goes beyond annotations by detailing the non-obvious puzzle mechanism: if challenge_id and answer are omitted, a fresh puzzle is returned, requiring a subsequent call. This fully discloses the interactive behavior, which is critical for correct invocation.

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 three sentences: purpose, requirement, and two-step flow. It is front-loaded, concise, and contains no extraneous information.

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?

The description covers the core puzzle workflow and the destructive nature, but it omits details about the return on success or failure, and the session_token parameter is not addressed. Given the lack of output schema, some aspects are left to inference.

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 adds meaning to challenge_id and answer by linking them to the puzzle, but it does not explain the session_token parameter. With no schema descriptions (0% coverage), the description partially compensates but leaves a gap for one parameter.

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 the tool removes a registered contact endpoint, which matches the name 'bardo_contact_delete'. However, it does not elaborate on what a 'registered contact endpoint' is, leaving some ambiguity for agents unfamiliar with the domain.

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 explains the step-up puzzle requirement and the two-step process if the puzzle is not provided, but it does not provide guidance on when to use this tool versus its siblings (e.g., bardo_contact_get, bardo_contact_set) or any exclusion criteria.

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