Find the silence worth cutting

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

With no annotations, the description carries the full burden. It discloses the per-call cost, that 'the expensive half is not redone' (implying caching or reuse), and that it returns spans and savings estimates. This is transparent for a read‑only analysis tool, though limits like max input size or error handling are not mentioned.

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 delivers core purpose in the first sentence, then adds essential usage and cost info in a second sentence. No redundant words; every sentence earns its place. It is front‑loaded and efficient.

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 tool has 3 optional parameters and no output schema. The description explains the input options (VTT or segments), the pipeline from transcribe_url, and the nature of the output (spans and saving estimate). It lacks a precise specification of the return format, but the description is sufficient for an agent to invoke the tool 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 description coverage is 100%, so baseline is 3. The description adds context about using segments from transcribe_url and the cost, but does not significantly expand on what the parameters mean beyond the schema. The value comes from pipeline guidance rather than parameter detail.

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 returns 'the spans of dead air and how much of the runtime cutting them would save,' which is a specific verb+resource. It distinguishes itself from the sibling 'transcribe_url' by focusing on silence detection rather than transcription.

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 explicitly tells the agent to 'feed it the segments transcribe_url returns,' establishing a clear pipeline. It also highlights the cost advantage ($0.002 vs. transcription cost). However, it does not explicitly state when not to use this tool (e.g., if no subtitles or timings are available).

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