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

Beyond the annotations it discloses that this is best-effort with a warnings list naming what could not carry (masks, blend modes, effects, ramps, text styling), that reference media expires 7 days after last use, that the call is long-running via task or job_id, and that the result carries a signed download URL. The one gap is that destructiveHint=true is never explained — nothing says what gets destroyed or how overwrite relates to it.

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?

Front-loaded with the purpose, then the lossless alternative, then caveats, then media modes, then the async mechanics — a sensible order with no filler sentences. The telegraphic, parenthetical style ("(masks, blend modes...)", "(the result warns)") is dense but occasionally reads as notes rather than prose.

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 long-running export with an output schema and a warnings channel, the description covers what an agent must decide before calling: format, media mode, and how to handle the async result. Return format is legitimately delegated to the output schema, and the lossless-vs-lossy fork is resolved.

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 67%, so the schema already documents the enums. The description restates format and media semantics rather than adding to them, though it does add the 7-day expiry rationale for reference media. It says nothing about filename, overwrite, or idempotency_key, which is the un-covered third.

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?

"Write the edit for another editor" states a specific verb and outcome, then enumerates the concrete artifacts (fcpxml, otio, edl, srt/vtt). It explicitly distinguishes itself from timeline.get ("the lossless copy") and implicitly from export.video by naming the interchange formats, so an agent can pick it out of a 60+ sibling list.

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 gives the selection rule for every format by naming the target application (FCP/Resolve, Premiere/OTIO, CMX 3600, captions) and routes lossless copying to timeline.get. It also states when to choose media collect over the default reference, with the reason (handing the edit to another machine).

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