Transcribe Audio / Video with Whisper

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

Annotations already cover the safety profile (not read-only, open-world, non-idempotent, non-destructive), so the description's job is to add context. It adds the return contract (PredictionResult with text_output), the curated model keys and default, and the language auto-detect default. It doesn't mention cost or the async/polling flow explicitly in prose (that lives in the timeout_ms schema), which keeps it just short of a 5.

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 a compact Args block and a one-line Returns. It mirrors the schema somewhat redundantly but stays short and scannable with no filler.

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 tool with no output schema, the description supplies the return shape and the key model-selection semantics; the only gaps (download flag, timeout/polling path) are documented in the schema. An agent has enough to call it correctly.

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 86%, so the schema already documents all seven parameters well and sets the baseline at 3. The description adds a concrete extra_input example ({batch_size: 24}) and clarifies the model key semantics, but it omits download and timeout_ms entirely, so it does not fully compensate beyond the schema.

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 (transcribe audio/video to text) plus the execution backend (Whisper-family models on Replicate). An agent can distinguish it from replicate_generate_speech and replicate_generate_audio without opening a 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?

The purpose implies when to use it (speech-to-text), but there is no explicit guidance on when to prefer it over siblings like replicate_generate_speech, replicate_run_model, or replicate_get_model_schema for a custom Whisper model. Usage is implied rather than stated.

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