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

Goes well past the annotations by disclosing the credit price (10 credits, free at 30 seconds or less), that score_id reuses credits and returns needs_confirmation creating nothing without consent, and that the original score stays intact. These cost and consent mechanics are exactly the behavior an agent cannot infer from readOnlyHint=false / destructiveHint=false.

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, front-loaded with the source enumeration before the cost rule. The second sentence is cramped ('Audio or video is the whole piece') and compresses the cost exception into a parenthetical, costing a little readability but no real waste.

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?

With 12 parameters, nested objects, and no output schema, the definition covers the highest-risk facts (cost, consent gate, needs_confirmation, original preserved). It leaves the returned artifact and the band review flow to the schema, which is acceptable given full schema coverage.

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 the parameter documentation burden is already met. The description adds only the credit-cost framing that ties to the source choice; it does not explain preview, provider, or pro_options beyond what the schema says, so baseline 3 applies.

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 concrete verb+resource ('Make a new score') and enumerates the three mutually exclusive sources (file, url, score_id), which lets an agent see this is the umbrella transcription entry point. It never names the near-siblings transcribe_attachment / transcribe_link / transcribe_again, so it does not fully disambiguate which tool to reach for.

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?

Gives real exclusions: score_id only 'when the user asks, never merely to fix notation', and preview only when the user asks to try one first. It also gates audio/video as 'the whole piece'. It does not say when to prefer this over the dedicated transcribe_link or transcribe_attachment siblings.

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