recommended_models

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It only says the tool returns 'pre-filtered best choices,' but does not clarify whether this is a read-only operation, what the result format looks like, whether it reflects real-time availability, or whether any side effects or prerequisites exist. For a simple retrieval tool this is thin.

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 well-structured with a one-line summary, automatic triggers, task types, and a parameters note. It is easy to scan and front-loads the core purpose. Slight redundancy exists between 'Get recommended' and 'Pre-filtered best choices' and between the first trigger and 'User asks for model recommendations,' but it remains tight.

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 a single required parameter, no annotations, and no output schema. The description explains what the tool does and what input to provide, but it does not describe the return shape or what the agent should do with the results, such as whether it returns model IDs, names, or full metadata. This leaves an agent guessing about downstream use.

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 provides only the parameter title 'Task Type' with no description, so the description must compensate. It does so by explaining task_type as 'What the model will be used for' and listing valid values: research, coding, analysis, writing, summarization, orchestrator, worker. This adds meaningful guidance beyond the raw schema.

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 verb and resource: 'Get recommended OpenRouter models for a specific task type.' It clearly differentiates this from sibling tools like list_models by framing it as pre-filtered recommendations rather than a full catalog browse. The listed task types further anchor what the tool covers.

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 description provides an explicit 'AUTOMATIC TRIGGERS' section with concrete scenarios such as 'What model should I use for X?' and 'Choosing models for a session without browsing the full catalog.' It gives clear context for when to call, though it does not explicitly mention when not to call or name alternative tools such as list_models.

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