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

Annotations indicate readOnlyHint=false, openWorldHint=false, idempotentHint=false, destructiveHint=false. The description adds significant behavioral context: complete=false gives changed-section proof only, complete=true creates the complete stored video even on first call, and quality=approval implies a full render from original. It also notes how to retrieve the result via watch_video or download_url. It stops short of stating side effects like cost/time, but the core behavior is well disclosed.

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?

Every sentence adds necessary information. The description front-loads project scoping, then explains the two modes, then quality implications, then retrieval. There is no filler or repetition. It is dense but efficient.

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 rendering tool with no output schema and 3 params, the description covers all essential aspects: what it does, the two completion modes, quality behavior, how to retrieve the result, and the job-status tool. An agent would know exactly how to invoke it and what to expect, including the first-call behavior for complete=true.

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 description). The description compensates fully: it explains that project_id is the required immutable scope (copy from list_projects/open_project/project_state, never the active-project pointer), quality=approval implies complete=true and draft is inexpensive 480px, and complete=false vs true semantics. This exceeds what the schema provides.

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 clearly states the tool renders evidence for the current immutable EDL, with explicit project scoping. It distinguishes its purpose from retrieval tools like watch_video and download_url, and from job-status via wait_for_job. The verb 'render' plus resource 'preview' is specific and unambiguous.

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 provides explicit guidance on when to use complete=false vs complete=true, the implications of quality=approval (implies complete=true, renders from original at up to 720x1280 portrait), and that draft is the inexpensive 480px preview. It also names alternative retrieval methods and clarifies that complete=false does not create a watchable complete preview.

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