advance_proof_guided_context

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

The description discloses several behavioral traits: the operation is durable and idempotent, continuation returns a specific status, terminal returns verified output, and no provider call is performed. These details add significant context beyond the absent annotations. However, it does not mention error conditions or required prior state (e.g., session from prepare_proof_guided_context).

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 concise (4 sentences) and front-loaded with the core purpose. It could benefit from breaking into sections (e.g., parameters, behavior) but is efficiently written without waste.

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 explains the output types (continuation vs terminal) and idempotency, but it omits critical context such as the need for a session created by 'prepare_proof_guided_context', the format of model_output, and the exact structure of the output schema. Given the complexity and the presence of an output schema, more completeness is expected.

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 0% schema description coverage, the description bears full responsibility for explaining parameters. It does not mention session_id, model_output, or idempotency_key at all, leaving agents without guidance on what each parameter represents or how to construct them.

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 states 'Verify one model round and return exact evidence or a final answer,' which is a specific verb+resource. It explains continuation vs terminal responses, clearly indicating the tool's role in the proof-guided context workflow. However, it does not explicitly distinguish this from sibling tools like 'verify_beliefs' or 'verify_response', leaving some ambiguity.

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?

No guidance is provided on when to use this tool versus alternatives such as 'verify_beliefs' or 'verify_response'. The description focuses on behavioral details but omits when to invoke or when not to, leaving an agent without clear selection criteria.

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