CLIPCLIPER

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

Annotations only declare readOnlyHint and openWorldHint, so the description carries the burden of behavioral disclosure. It explicitly states that the video is transcribed first if needed (same cost and async behaviour as get_transcript), that chapters are free and cached, and implies async behavior via the wait_seconds parameter. This adds significant context beyond the annotations without contradiction.

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?

Two sentences, no fluff. The first sentence front-loads the core purpose and output structure; the second adds behavioral context. Every word earns its place, making it concise and well-structured.

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?

The description explains the output shape (chapters with start/end, title, summary) and the async/cost context, which covers the key information an agent needs. It does not explicitly mention the 'processing' status that wait_seconds can return, but that is covered in the schema. Given the lack of an output schema, the description provides adequate context 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?

The schema description coverage is 100%, with all 5 parameters already documented in the schema. The description does not add any parameter-specific meaning beyond what the schema provides. Per the rubric, with high schema coverage the baseline is 3, and no additional value is added.

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 (split) and resource (public video into topic chapters) with details on output (start/end seconds, title, one-line summary). It also differentiates from get_transcript by noting it uses the transcript and has same cost/async behavior, clearly distinguishing its purpose from the sibling 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 gives context by comparing to get_transcript (same cost and async behaviour) and notes that chapters are free/cached, which implies a good use case. However, it does not explicitly state when to use this instead of get_transcript or suggest_clips, nor any when-not conditions. The guidance is clear enough but lacks explicit exclusions.

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

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

Annotations provide readOnlyHint=true and openWorldHint=true, and the description goes well beyond these by disclosing asynchronous behavior (returns 'processing'), caching (24h per url), pricing (pack minutes), and limits (15 min without key, daily IP limit). No contradiction with annotations; it adds substantial behavioral context.

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 three sentences, each adding value: purpose, async retry, caching, and pricing/limits. It front-loads the core function and avoids fluff. Slightly dense but efficient and well-structured.

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 tool's complexity (async, pricing, limits, multiple formats) and lack of an output schema, the description covers the key behaviors and mentions the transcript with timestamps. It does not describe the full response structure, but the format parameter covers output variants. It is adequate for an agent to call correctly.

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 100%, so all parameters are already well documented in the schema. The description adds behavioral context (e.g., 'just call again' relates to wait_seconds) but does not add meaning beyond what the schema provides. Baseline 3 is appropriate when schema does the heavy lifting.

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 ('Download') and resource ('public video') and explicitly names the output ('full transcript with timestamps'). It distinguishes itself from siblings (get_chapters, suggest_clips) by being about the full transcript, so an agent can tell it apart without opening other 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 gives clear context about when to call again (async processing) and mentions limits (15 min without key), but it does not explicitly state when to use this tool versus get_chapters or suggest_clips, nor does it provide exclusions. Usage is implied by the purpose but not contrasted with alternatives.

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

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

Annotations already mark this as read-only and open-world, so the description adds value by disclosing that transcription may happen first, that behavior matches get_transcript, and that suggestions are free per call. This goes beyond what the annotations alone convey. No contradiction with annotations.

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 compact, front-loaded with the core capability, and every sentence adds value: what it returns, when it transcribes, and cost/async behavior. No filler or redundant restating of the title.

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 no output schema, the description covers the return shape (seconds, title, reason), cost, and async behavior. Combined with detailed parameter descriptions and annotations, it is largely complete, though it does not explicitly explain the 'processing' status flow that wait_seconds references.

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 already covers 100% of parameters with descriptions, so the baseline is 3. The tool description adds some high-level output context but does not enrich the meaning of specific parameters like count, wait_seconds, or reason_language beyond what the schema provides.

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 names a specific action ('Find'), a specific resource ('most shareable moments of a public video'), and concrete deliverables: start/end seconds, a hook-style title, and a reason. This clearly differentiates suggest_clips from the sibling tools get_transcript and get_chapters.

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 gives useful context by noting it transcribes the video first and shares cost/async behavior with get_transcript, but it never explicitly states when to choose this tool over the siblings or when not to use it. Usage is implied by the purpose rather than clearly routed.

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