recommend_models

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

With no annotations, the description carries the safety burden. It communicates a read-only external fetch from OpenRouter and that results depend on live benchmarks, which covers the main behavioral traits. It does not mention auth/rate-limit implications, but for a simple fetch the key traits are disclosed.

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 EN/PL sections are each two sentences and front-load the core action before the usage note. The duplication is minor and the labels keep it clear.

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?

The tool has an output schema and only two optional parameters, so the main missing piece is parameter semantics. Purpose and usage are clear, but an agent cannot know what task_type values are valid or how limit affects results, leaving a real gap.

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?

The schema has 0% description coverage and the description never explains `limit` or `task_type`, nor enumerates valid task types. The only indirect hint is the default `task_type: coding`, which is not enough to compensate.

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 opens with a specific action and object: 'Fetches the most cost-effective and capable models from OpenRouter based on live benchmarks.' It also differentiates its role by pointing to run_subagent, making it clear this tool is a model-recommendation helper rather than a task runner.

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?

It explicitly instructs agents to call this tool before run_subagent when uncertain about the model ID or when optimizing cost/quality. This states the condition and the alternative tool, which is sufficient guidance for selection.

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