consensus_check

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

The description adds the behavioral detail that the tool 'starts validation jobs,' which is important beyond the annotations. However, it does not explain whether the operation is asynchronous, how results are retrieved, whether external provider CLIs execute arbitrary work, or what 'destructive' side effects might occur beyond starting jobs.

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 with no filler. It front-loads the core purpose and parenthetically adds the important side effect of starting validation jobs. Every element earns its place.

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?

With no output schema, the description should explain what the caller receives back and how results relate to the job lifecycle. It only says 'starts validation jobs,' leaving the agent to infer return values, job IDs, and how to retrieve consensus outcomes from sibling tools like validation_receipt or job_status.

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 description coverage is 100%, with clear descriptions for claim, models, and select. The tool description itself adds no parameter-level meaning, so the baseline of 3 is appropriate; the schema carries the semantic weight.

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 names a specific action ('Ask provider CLIs'), a resource ('provider CLIs'), and the object of the action ('whether they agree or disagree with a claim'). It is more than a tautology and aligns with the tool name, but it does not clearly differentiate this tool from closely related siblings such as validate_with_models, second_opinion, or compare_answers.

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 about when to use this tool versus the many sibling validation/consensus tools, nor are exclusions or prerequisites mentioned. The only implicit usage signal is the phrase 'starts validation jobs,' which hints at a workflow but does not say when this should be chosen over alternatives.

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