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

Annotations only declare readOnlyHint and openWorldHint, so the description usefully adds the pricing model ('Cost: 2 credits, charged only when a call succeeds') and the return shape (SRT/VTT text plus language, duration, cue count). It stops short of media constraints (size/duration limits) but covers more than the annotations alone.

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?

Four tight sentences with zero filler, front-loaded with the action and output, followed by usage and the alternative. Every sentence carries distinct 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?

With no output schema, the description correctly compensates by describing the return contents (subtitle text, language, duration, cue count) and the billing behavior. Only minor operational details such as supported media limits or async/polling behavior are absent.

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 all three params (format, language, audio_url) are already documented with defaults and an enum. The description restates that output comes in SRT or VTT but adds no parameter-level syntax or constraint beyond the schema; 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 specific verb+resource ('Generate SRT/VTT subtitles from audio or video') and immediately distinguishes itself from the transcription siblings. An agent can tell what this produces (caption files) versus a plain transcript without opening the 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?

Gives explicit use context ('Use to caption a video or an audio file') plus a named alternative with the selecting condition ('For a plain transcript use stt or transcribe'). Both the when and the when-not are covered.

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