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

Beyond the annotations (which only say non-readonly, non-destructive), it discloses that uncached media will be transcribed as a side effect, that the timeline is mutated only when apply is set, and what the response looks like in each case. The ordering caveat about later tracks drawing under footage is exactly the kind of non-obvious behavior an agent would otherwise get wrong.

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 purpose is front-loaded and every sentence carries real information (caching, return types, ordering). It is tightly packed and somewhat run-on; the final clause about drawing order requires re-reading, but nothing is padding.

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 does the necessary work of explaining both possible return values (summary vs JSX) and the timeline side effect. Gaps remain around preset ids and the three undocumented parameters, but the complex parts of the tool are covered.

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 50%: apply, preset, and project are documented in the schema, while language, trackName, and wordsPerCaption are undocumented in both places. The description clarifies apply's dual semantics and hints at preset's role (restyle), but adds nothing for language or wordsPerCaption.

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?

It names a specific artifact ('a <track kind="caption"> for the current timeline') built from a specific source (media transcripts), and it distinguishes the two execution modes. An agent can tell this apart from transcribe_media and apply_timeline without opening any 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?

It clearly states the apply/no-apply choice and what each returns, and warns that the returned JSX is meant for apply_timeline and that track ordering determines visibility. It stops short of an explicit 'use X instead when...' against siblings like transcribe_media, but the conditions for each mode are spelled out.

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