export_subtitles

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

Annotations already declare readOnly=false, destructive=false, openWorld=false, so the safety profile is covered. The description adds genuinely useful context beyond that: it creates a new file rather than modifying the project, it exports edited wording/line-break/timing state, and it requires burned-in captions to be disabled. It does not say what happens if outputPath already exists.

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 short sentences with no filler, opened by the core action and format set. Each sentence carries distinct information: what is exported, the precondition, and the side effect.

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 write operation with four required parameters and no output schema, the definition covers the essentials but leaves gaps: it does not state whether an existing file at outputPath is overwritten or rejected, nor what the tool returns on success or failure. Adequate for selection, thinner for confident invocation.

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 only 50%: projectDir and expectedRevision are documented in-schema, but outputPath has no description anywhere. The description partially compensates by naming the SRT/VTT formats (mapping to the enum) and implying that a new file is written at a caller-supplied path, which gives outputPath implicit meaning.

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 ('Export edited caption wording, line breaks and timeline timing') plus the two output formats (SRT, WebVTT), which clearly separates it from export_timeline and export_render. It stops short of naming those siblings, so differentiation is inferred from the resource rather than stated.

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?

'Works when burned-in captions are disabled' is a real precondition that tells the agent when this tool is applicable. However, there is no explicit guidance on when to prefer this over export_timeline or export_render, and no statement of failure conditions.

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