detect_duplicates

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

With no annotations provided, the description caries the full burden of conveying behavior. It states the tool 'finds' clips, implying a read operation, but does not specify that it is non-destructive, nor what the response contains (e.g., list of clip IDs). No details on performance, side effects, or failure modes.

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, short sentence with no unnecessary words. It effectively conveys the core purpose. However, it could be slightly expanded (e.g., mentioning modes) without losing conciseness. Front-loading is adequate.

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 no output schema and sibling tools, the description lacks essential context: it does not explain what the tool returns (e.g., list of duplicate groups), how modes differ, or how it integrates with other detection tools. The minimum requirement for a 2-parameter tool would include output description.

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 100%, with both parameters described adequately (filepath as path, mode as enum). The description adds no extra meaning beyond the schema, such as default behavior of 'same_source' or how the mode affects results. Baseline 3 is appropriate as the schema does the work.

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 detects clips using the same source media, indicating duplicate detection. It distinguishes from sibling detection tools (e.g., detect_gaps, detect_flash_frames) by specifying 'duplicates' via source media. However, it does not mention the modes or output format, leaving some ambiguity.

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 no guidance on when to use this tool versus alternatives like detect_gaps or detect_silence_candidates. There is no explicit context about prerequisites (e.g., open timeline) or when not to use it. The agent must infer the right situation from the tool name alone.

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