Samplecut

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

Adds behavior beyond the annotations: links expire after about an hour and the user must re-request, format defaults to mp3 with wav as the alternative. These are meaningful operational facts an agent needs. It doesn't cover auth or rate limits, but annotations already declare openWorldHint=true and destructiveHint=false.

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?

Front-loaded with purpose, then response guidance, then expiry and parameter defaults. Every sentence carries information; it is slightly dense but not padded.

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?

Return keys (download_url, editor_url) and link expiry are explained, and an output schema exists so return structure needn't be detailed. Covers the essentials for calling and acting on the result, with only auth/permission context 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 100%, so the baseline is 3. The description still adds value by clarifying the omit-both-for-full-track interaction and the mp3 default/wav option, which reinforces the schema's conditional duration_sec semantics.

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?

States a specific verb and resource ('cut audio') plus the accepted source platforms and the primary return artifact (a short-lived download link). It is clearly distinct from get_transcript, but it never explicitly names or contrasts the sibling, so it stops short of a 5.

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?

Gives concrete usage direction: prefer download_url for cut/download requests, offer editor_url when the user wants to tweak the selection, and omit start_sec/end_sec for the full track. There is no explicit when-not or alternative-tool guidance (e.g., 'use get_transcript instead for text'), so it is clear context rather than full routing.

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 declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so safety is covered. The description adds genuinely new behavior beyond the annotations: caption availability is conditional on the platform, the available=false case must not be hallucinated around, and lang defaults to en. The 'No job_id is returned' note is useful but only marginally so given an output schema exists.

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?

Front-loaded with the core action, then the chaining instruction, then the failure guard, then two small footnotes. No sentence is filler; each adds a distinct operational fact.

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?

Beyond the schema and annotations, the description supplies the workflow handoff to cut_audio and explains how to consume the returned segments, which is exactly what an agent needs for a step in a multi-tool pipeline. An output schema exists, so return-value documentation is correctly not duplicated.

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%, so both url and lang are already documented at the same level the description restates (BCP-47, default en). The start_sec/end_sec references describe output segments rather than input parameters, so they help context but not parameter semantics. Baseline 3 is correct when the schema carries the parameter burden.

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?

States a specific verb and resource (fetch timestamped captions) plus the scope of supported platforms (YouTube, TikTok, Instagram) and the conditional 'when the platform provides them'. It also positions itself in the workflow relative to the only sibling, cut_audio, so an agent can tell the two apart without opening either schema.

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?

Explicitly routes the agent: use segment start_sec/end_sec to choose a cut range, then call cut_audio with the same URL and those times. It also defines the failure path — when available is false, do not invent lyrics or timestamps and tell the user to pick times another way. This is when-to-use, how-to-chain, and when-not behavior in one place.

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