transcribe_media

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

With no annotations, the description carries the full burden of behavioral disclosure. It discloses server-side download/extraction, async behavior (returns jobId, poll check_transcription), and cost scaling with a cap mechanism. This goes beyond a simple 'transcribe' statement and provides useful operational context, though it could mention failure modes or rate limits.

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?

Three sentences, each earning its place: purpose, server-side handling with no external tools, and async/cost guidance. Information is front-loaded with the main action, and no fluff or repetition. Exceptionally concise for the amount of context provided.

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 covers the essential aspects for a complex async tool: what it does, how to handle the async pattern (jobId + polling), cost implications, and the lack of external dependencies. Even without an output schema, the agent knows how to initiate and retrieve results. This is highly complete for the given complexity.

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 baseline is 3. The description adds value by explaining maxCostDollars as 'cap spend on long media,' which enriches the schema's generic description. It also clarifies the tool's output (timestamped segments) indirectly. Language and url are straightforward from schema, so the added context for cost is meaningful.

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 function with a specific verb and resource: 'Transcribe the audio of any video/audio URL... to text with timestamped segments.' It explicitly differentiates itself from siblings by mentioning 'Async: returns a jobId immediately; poll check_transcription for the transcript,' which contrasts with the polling tool.

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 clear context for when to use this tool (to transcribe media from various sites) and explicitly names check_transcription as the alternative for obtaining results. It also advises setting maxCostDollars for long media. However, it does not explicitly mention when not to use it relative to other import tools, though the async/cost guidance largely covers usage.

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