validate_with_models

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

Discloses the key behavioral trait beyond annotations: the call is asynchronous and merely starts jobs whose results must be fetched separately via job_status/job_result. Annotations already carry the safety profile (destructiveHint=true, readOnlyHint=false), and the description does not contradict them. It does not explain what 'destructive' means here (e.g., consuming provider quota/credits), but the operationally critical behavior is covered.

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?

Two sentences totaling roughly 30 words, with the core purpose front-loaded and the operational caveat second. Every clause earns its place; the 'not llm_job_*' disambiguation is high-value given the sibling set.

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 no output schema and an async job lifecycle, the description covers the critical chain (start → poll with job_status → collect with job_result) and flags the misleading llm_job_* family. Gaps remain: it never states what the call returns (presumably a job identifier), does not flag the cost/quota implications behind destructiveHint, and does not differentiate from the validation-family siblings. Overall it is complete enough for correct invocation of the core flow.

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%, so the schema already documents all five parameters; per the baseline rule this is a 3. The description adds only the 'two or more' multiplicity signal, which sits slightly at odds with the schema's minItems:1 (though the default of two providers reconciles it). No material parameter semantics are added beyond what the schema provides.

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 action ('Ask two or more provider CLIs to independently validate a question') with a clear resource and mechanism. The 'not llm_job_*' note distinguishes the result-collection path from a large family of sibling tools, and the multi-provider framing separates it from single-model tools like ask_model and the various *_request tools.

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?

Provides explicit post-invocation workflow guidance: poll with job_status, collect with job_result, plus an explicit exclusion ('not llm_job_*') that prevents a likely mistake given the many llm_job_* siblings. However, it does not name alternative validation tools (e.g., second_opinion, consensus_check, compare_answers) or state when to choose them instead.

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