Clip Transcript

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

Goes well beyond the annotations (which only say readOnly=false, destructive=false) by disclosing credit costs per path, the zero-charge case, the required confirm=true, and the reassuring note that read-like POSTs do not publish to social platforms. This is exactly the paid-API context an agent needs.

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 the fallback rule, then cost/auth. Mostly efficient, though the cost figures are restated between the description and the schema, and the final sentence about publishing is a slight tangential add.

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?

With no output schema, the description helpfully enumerates transcript_source values and credit outcomes, and covers auth (confirm) and cost. It doesn't describe the full transcript payload shape, but for a read-like transcript fetch that is a minor gap.

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 3-baseline applies, but the description adds real value by tying use_ai_as_fallback to its cost consequence (10 credits) and the native-vs-AI fallback behavior, plus explaining transcript_source's possible values. It adds meaning beyond the schema without needing to duplicate URL/account 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 ('Gets a transcript from a public Kick clip') and implicitly distinguishes itself from the sibling kick_clip (clip metadata) by naming the transcript output. An agent can tell what it retrieves without opening the 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?

Explains the conditional path clearly: native captions are checked first, and use_ai_as_fallback=true only triggers AI when native is unavailable. It also states credit costs and the confirm=true prerequisite. It stops short of naming sibling alternatives (e.g., twitch_clip_transcript / kick_clip) for cross-platform selection, so a 4 rather than 5.

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