index_video

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

Annotations only provide idempotentHint, but the description discloses latency (3-7 minutes, longer for long/full), a 10-minute timeout, default scene detection behavior, pipeline side effects, and prerequisite status. None of this contradicts the idempotentHint annotation, and it gives the agent crucial expectations for a long-running tool.

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 information-dense but well-organized: purpose, expected duration, pipeline modes, detection behavior, preconditions, and input modes. Each sentence contributes operational value, and the most decision-relevant details (timeout, status prerequisite, exactly-one parameter) are placed prominently.

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 tool with 5 parameters, no required fields, no schema-level descriptions, and meaningful sibling interdependencies, this description covers purpose, timing, timeout, prerequisites, pipeline options, defaults, and downstream tool enablement. Output behavior is covered by the output schema, and the only minor gap is the rationale parameter, which is optional and non-essential for correct invocation.

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%, so the description must carry parameter meaning. It does for pipeline, video_id vs file_path, and scene_detection, including the 'exactly one' rule and defaults. The only paramter left unexplained is rationale, which is optional but still undocumented in both schema and description.

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 verb and resource ('Index a video') and goes further by enumerating the three pipeline modes and the downstream tools they enable (search_videos, ask_video, all tools). This clearly distinguishes index_video from the sibling tools while making its role in the workflow obvious.

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 gives explicit operational guidance: check the video is in 'uploaded' status and use get_video, provide exactly one of video_id or file_path, pick a pipeline, and optionally disable scene_detection. The description also implies sequencing by noting which downstream tools each pipeline enables. This is far beyond minimal viable usage guidance.

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