媒体理解（图/视频/音频 → 文本）

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

With no annotations, the description carries the full burden. It discloses asynchronous submission, default 60s wait, direct return vs task_id for long tasks, media type auto-detection, and model routing. However, it does not mention rate limits or detailed error conditions beyond invalid model.

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 a single paragraph that front-loads the core purpose and then provides key details. It is concise and logically ordered, though could benefit from slight structuring for readability.

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?

Given the complexity (9 params, no output schema), the description covers purpose, input types, async behavior, model source, and error handling. It compensates for missing output schema by describing return types. Minor gaps like rate limits and full error scenarios are absent.

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 78%, so baseline is 3. The description adds value by explaining the async logic (wait_seconds, task_id return) and the model registry distinction, which goes beyond what the schema provides. It does not repeat parameter constraints but contextualizes their use.

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 the tool's purpose: analyzing media (image/video/audio) using multimodal LLMs to output text, and explicitly distinguishes it from the host model's limitations. It differentiates from sibling tools like ask_model (text-only) and generate_* 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?

The description explains when to use the tool (for media analysis), describes the asynchronous behavior and timeout handling, and notes that models come from a separate registry from generation tools. While it doesn't explicitly mention when not to use, it provides clear contextual guidance.

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