transcribe

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

Annotations already cover safety (readOnlyHint false, idempotentHint true, openWorldHint true) and the schema covers the max_credits budget failure. The description adds genuinely new behavioral context: per-mode credit costs and the 'paid plans' restriction on AI transcription, which an agent needs to avoid surprising charges.

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, zero waste: the action and return value come first, then the cost/mode decision information that actually affects the call. Each clause earns its place.

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 5-parameter create-job tool with full schema coverage and annotations, the description covers action, return value, and cost tradeoffs. It doesn't describe the returned job object, but with no output schema a brief pointer to get_job would have closed the last 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 description coverage is 100% and every parameter is documented, so the schema does the heavy lifting and the baseline is 3. The description's mode cost explanation largely restates the mode parameter's own description, adding no syntax or format detail the schema lacks.

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 ('Submit'), specific resources (YouTube or TikTok URL), the service (TranscriptDock), and the outcome ('return the created job'). That outcome clause distinguishes it from get_job, which retrieves an existing job.

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 mode/cost breakdown gives clear guidance for choosing captions_only vs auto vs transcribe, including when auto falls back to AI. It doesn't explicitly exclude this tool in favor of siblings like get_video_transcript for already-submitted URLs, but the create-job framing implies that.

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