second_opinion

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

Annotations indicate destructiveHint=true and openWorldHint=true. The description adds the async job workflow (start, poll, collect) beyond annotations, but does not elaborate on side effects or the destructive nature. It provides basic behavioral context but not comprehensive.

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 a single sentence that efficiently conveys the action, async pattern, and follow-up steps. It is front-loaded and every part adds value with no unnecessary words.

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 tool with 3 parameters and no output schema, the description explains the workflow (start job, poll, collect). It implicitly tells the agent to expect a job ID and how to proceed. Could mention error handling or return format, but it's mostly complete given the context.

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?

Schema coverage is 100% with descriptions for all three parameters (model, answer, question). The tool description does not add additional semantics beyond 'review an answer', so it meets the baseline but does not enhance understanding.

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 action 'Ask one provider CLI to review an answer' with the specific resource (a validation job) and explains the async workflow (poll job_status, collect job_result). It differentiates from siblings by mentioning the 'second opinion' concept.

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 implies usage for getting a second opinion on an answer and describes the subsequent steps, but does not explicitly state when to use this tool versus alternatives like ask_model or specific model request tools. No 'when-not' guidance is provided.

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