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

The description is highly transparent about behavior: it is project-scoped, returns project identity, explains that complete=false yields only changed-section proof and is not watchable, that complete=true creates the stored video even on first call, and that quality=approval implies complete=true with specific resolution and rendering path. It also mentions wait_for_job and retrieval via watch_video/download_url. Annotations are minimal, so the description carries the full burden and does so thoroughly.

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 description is long but every sentence adds value: scoping, the effect of complete, the effect of quality, the Studio attachment, wait_for_job, and retrieval. It front-loads the critical 'PROJECT-SCOPED' constraint. Slightly verbose but efficiently dense.

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 tool with three parameters, no output schema, and minimal annotations, the description covers the key behavioral aspects: project scoping, parameter semantics, job waiting, and retrieval paths. It leaves little ambiguity for an agent to call it correctly. The only minor gap is a precise return format, but it states 'returns the project identity with its result,' which is adequate.

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 33% (only project_id has a schema description), but the description fully explains the semantics of quality and complete. It defines quality levels (approval vs draft) with resolution and rendering implications, and complete with the distinction between proof-only and full video. This fully compensates for the schema's lack of documentation.

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 opens with 'PROJECT-SCOPED' and states 'Render evidence for the current immutable EDL,' which is a specific verb, resource, and scope. It clearly distinguishes from retrieval tools like watch_video by noting 'MCP clients can retrieve it with watch_video or download_url,' implying this tool creates the preview rather than retrieves it.

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 description explains when to use different parameter values (complete=false vs true, quality=draft vs approval) and notes the behavior of wait_for_job and re-calling to review existing results. However, it does not explicitly name alternative tools or state 'use this instead of X'—the distinction from watch_video is implicit rather than explicit.

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