ask_model

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

The description discloses a key behavioral trait beyond the annotations: the call 'starts a validation job' rather than returning a direct synchronous answer. This aligns with openWorldHint=true and explains the side-effecting nature. However, with destructiveHint=true, it does not clarify what consequences follow (resource consumption, state written, job lifecycle), leaving the most surprising annotation unexplained.

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?

A single sentence with zero filler. The action verb leads, and the two most decision-relevant qualifications ('simplified validation surface' and 'starts a validation job') immediately follow. 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 carries the burden of explaining what the caller gets back, but it stops at 'starts a validation job' without mentioning the job reference, receipt, or how to retrieve results. Sibling names (job_status, job_result, validation_receipt) hint at the workflow, but the description itself leaves the follow-up loop open for a tool marked destructive and open-world.

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%, including a rich explanation of the select parameter with its 'fails closed' behavior, so the baseline of 3 applies. The tool description itself adds no parameter-level meaning, but the schema already carries the full load.

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 a specific verb+resource ('Ask one provider CLI a question') and adds a differentiating scope ('simplified validation surface... starts a validation job'). This clearly separates it from direct provider-request siblings (claude_request, codex_request) which don't go through the validation surface, and from multi-model siblings (compare_answers, consensus_check) which involve more than one provider.

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 phrase 'simplified validation surface' gives implied context that this is the lightweight path for single-provider questions inside validation workflows. However, it never names alternatives or states when not to use it — e.g., when to use validate_with_models, second_opinion, or the direct provider request tools instead. The select parameter description adds routing detail but only for the LCR sub-option, not for tool selection.

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