Compare model responses

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

Annotations declare non-read-only, open-world, non-idempotent, non-destructive, but the description adds context annotations cannot: it performs local inference, returns JSON comparisons, and results are 'best-effort if a model is cold' — a real reliability caveat the agent should know before interpreting output. It does not discuss cost or timeouts, so it is not exhaustive.

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?

Front-loaded with the core action and comparison criteria, followed by the routing alternative. 'Returns JSON with comparisons' is largely redundant given an output schema exists, a small amount of waste in an otherwise tight four-sentence description.

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 an output schema present, the description need not explain return values, and both parameters are fully documented in-schema. It covers the essential behavioral caveat (cold models) and the alternative tool, leaving only minor gaps like expected latency or model-count limits.

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 both prompt and models documented in-schema, so the schema carries parameter meaning. The description only restates that the same prompt goes to every listed model; it adds no format, count, or naming guidance for the models array.

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?

States a specific verb and resource (send the same prompt to several local models) plus what is compared (latency and reply preview), which an agent can distinguish from sibling chat_with_model at a glance. The scope — multi-model comparison rather than single-model conversation — is unambiguous.

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?

Explicitly routes the agent to chat_with_model when a full single-model conversation is wanted, which is the key sibling decision. It lacks any when-not-to-use guidance (e.g. cost, number of models, cold-start avoidance), so it stops short of a full routing rule.

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