model_info

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

With no annotations provided, the description must disclose behavioral traits on its own. It does state that data comes from the OpenRouter endpoints API and that missing fields are returned as 'unknown'. It implies a read-only fetch operation, but it does not explicitly state that it makes no modifications, nor does it cover potential errors or rate limits. The disclosure of the external dependency and the 'unknown' fallback adds value, but the description does not fully characterize the tool's side-effect profile. Without annotations, this is a partial disclosure.

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 two sentences and gets straight to the point. The first sentence states the core purpose, the second explains the data source and handling of missing information. There is no fluff or redundant detail. Every sentence earns its place, and the most important information is front-loaded.

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 one-parameter read-only tool with no annotations, the description covers the essential aspects: what it does, the source of data, and the fallback for missing values. An output schema exists, so return format is implicitly covered. It doesn't address potential error cases or explicitly state that it is a read-only operation, but given its simplicity, the description is nearly complete. The main gap is the lack of explicit guidance on when to choose this over list_speech_models, but that is more of a usage guideline than completeness for calling the tool.

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 input schema declares a single optional string parameter 'model' with a default of an empty string, but provides no further explanation. The description directly explains the parameter semantics: if a model is named, details for that model are returned; otherwise, the configured default is used. This adds essential meaning beyond the schema and clarifies the behavior for both empty and non-empty values. It could go further by specifying the expected format (e.g., model ID or name), but it is largely sufficient.

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 clearly states it provides live details for a speech model, either the configured default or a specific one named by the user. It specifies the data points (pricing, tier, voice-cloning support) and the data source, distinguishing it from sibling list_speech_models which would list models rather than give details. The verb is implied ('get') but the resource is specific and the scope 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?

The description implies usage: you call it to get details about a specific model or the configured default. However, it does not explicitly mention when to use this tool versus list_speech_models or other siblings, nor does it provide any exclusions or conditions (e.g., 'use this when you need details, list_speech_models for a list'). The context is clear enough, but there is no explicit routing guidance.

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