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

With no annotations, the description carries the full burden and does it well: it discloses the resolution tradeoff (half-resolution), output format (MP4), cost (1 credit billed to the project owner) and a specific failure mode (INSUFFICIENT_CREDITS). The main gap is that 'Start' implies an asynchronous job but it never says a job/render id is returned or that render.status should be polled.

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 tight sentences, front-loaded with the core action, with cost and failure mode last. The only wasted token is the '(§11.8)' spec reference, which conveys nothing actionable to an agent.

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?

Cost, quality level, output format and error code are covered, but with no annotations and no output schema the definition leaves a real gap around what a 'start' call returns and how the result is retrieved (render.status / render.get_result exist as siblings). What happens to a previously rendered preview is also unstated.

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%: aspect and fit are already well documented in the schema, and the description only adds that they match render.final so framing is comparable. projectId is undocumented in both schema and description, leaving the required parameter's meaning to inference from 'the project's current timeline'. Baseline 3 is appropriate given the schema does most of the work.

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: 'Start a fast, half-resolution preview export of the project's current timeline to MP4.' It also explicitly contrasts itself with render.final ('same aspect/fit as render.final'), so an agent can separate the cheap preview path from the final render path without opening either 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?

The phrase 'so the framing can be checked cheaply' gives a clear reason to choose this over render.final before committing to a full render. It names the related tool but never states an explicit exclusion ('use render.final instead when...' or when preview is insufficient), so it stops short of full routing guidance.

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