Get clip captions

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

Beyond readOnlyHint=true, the description discloses that captions mirror the rendered video's lines and times including the intro, that they exist even when the style has captions off, that the return value is file text, and that a clip rendered before caption files returns a message pointing at rerender_clip. That stale-render behavior is exactly the kind of non-obvious trait the description must carry.

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, front-loaded with what the tool returns, then parameter nuance, then the failure case. Dense but every sentence earns its place; slight compression could improve readability.

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?

There is no output schema, but the description states the return value is file text and explains what that text contains. Combined with the stale-render case, an agent has everything needed to call it correctly and interpret the result.

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, but the description adds meaningful plain-language semantics: words: true yields karaoke-style word timestamps and only applies to VTT. That clarifies the interaction between the two optional parameters beyond what the schema states.

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 names a specific verb+resource (fetch the captions of a clip's last render) and pins down the exact artifact form (SRT or WebVTT file text). The phrase 'a clip's last render' distinguishes it from project-level transcript siblings such as get_transcript and get_project_transcript_file.

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?

It clearly states the context in which this tool applies (captions of the last render, intro included, regardless of style settings) and routes the stale-render case explicitly to rerender_clip. It doesn't explicitly contrast with get_clip or get_transcript, but the trigger conditions are clear.

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