understand_video

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

With no annotations, the description carries the full burden, but it only discloses the high-level outcome. It does not mention the server management behavior implied by server_url, manage_server, keep_server, model auto-download, ffmpeg dependencies, or the fact that outputs are written to disk and models may need to be downloaded.

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 one concise, front-loaded sentence with no filler. It clearly communicates the main action and result, though the brevity comes at the cost of critical contextual details.

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?

This is a complex tool with 18 parameters, no output schema, and no annotations, yet the description explains neither the output contract nor the significant side effects. An agent cannot confidently determine prerequisites, resource implications, or what 'persist an agent context' means in practice.

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 0% and there are 18 parameters, so the description must compensate but does not. It only loosely maps to file_path and keyframe-related parameters, and it says nothing about model, server, response_format, out_dir, or the many other parameters an agent must configure correctly.

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 states a specific, multi-part purpose: transcribe a local video, capture synced keyframes, and persist an agent context. This goes beyond a vague verb and helps distinguish it from sibling tools like transcribe_video and transcribe_audio, though it does not explicitly name which sibling does what.

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?

There is no guidance on when to use this tool versus transcribe_video, transcribe_audio, or transcribe_folder, and no exclusions or alternatives are mentioned. The phrase 'local video' implies one use case, but the agent is left to infer when the keyframe/context persistence capability should be selected.

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