transcribe_v2

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'Fast caption-based transcript' which hints at performance but doesn't specify speed, reliability, or error handling. It doesn't disclose authentication needs, rate limits, or what happens if captions are unavailable. The POST method implies a write operation, but there's no clarity on whether this creates new resources or has side effects.

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 extremely concise with just two sentences. The first sentence states the endpoint and core functionality, while the second provides key usage constraints. Every word earns its place with zero redundancy or fluff. It's appropriately front-loaded with the most critical information.

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 complexity (4 parameters including a nested object), no annotations, and no output schema, the description is insufficiently complete. It doesn't explain what the tool returns (transcript format, structure, or potential errors), doesn't cover all behavioral aspects, and leaves gaps in parameter understanding despite the schema doing some work. For a tool that presumably creates new transcripts, more context is needed.

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 75%, so the schema already documents most parameters well. The description adds minimal value beyond the schema: it mentions 'manual or auto captions only' which relates to the 'source' parameter but doesn't explain the 'auto (manual first, fallback to auto)' behavior detailed in the schema. No additional parameter semantics are provided, so it meets the baseline for high schema coverage.

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's purpose: 'Fast caption-based transcript (no ASR)' specifies it generates transcripts from captions rather than automatic speech recognition. It mentions 'manual or auto captions only' which further clarifies the input source. However, it doesn't explicitly differentiate from siblings like 'get_transcript' or 'list_transcripts' beyond the 'POST /api/v2/transcribe' endpoint reference.

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 some usage context: 'Use manual or auto captions only' and 'no ASR' implies when this tool is appropriate versus alternatives that might use ASR. However, it doesn't explicitly state when to use this versus siblings like 'get_transcript' (which presumably retrieves existing transcripts) or 'delete_transcript'. The guidance is implied rather than explicit.

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