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

Annotations already flag destructiveHint=true, but the description adds substantial context: the operation is not undoable, exactly what each action destroys, that library-saved renders survive a project/job delete, that assets are refused while in use unless forced, and that user confirmation is required. This is well beyond the annotation set.

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-loads the irreversible DELETE and its scope before the constraints, which is correct ordering. The trailing beta/tier detail (free accounts get 3 badged 720p exports, trials 2 clean exports a day, subscribers unlimited) is export-quota marketing irrelevant to a delete operation and dilutes the paragraph.

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 destructive, no-output-schema tool this covers the critical ground: what is destroyed per action, irreversibility, the force escape hatch, and the video_guide prerequisite. It doesn't state the return/confirmation shape or idempotency, but those are minor against an otherwise complete picture.

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 description coverage is 0%, so the description must carry the load and it does: action's three values are each defined (project/asset/job) and mapped to their id parameter (projectId/assetId/jobId), and force's effect ('unless force=true') is explained. Every meaningful parameter gains semantics beyond the bare schema types.

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?

Starts with a specific verb+resource ('Video Director DELETE (not undoable)') and then enumerates exactly what each of the three actions removes: a project with its history and renders, a library asset, or a single render job. An agent can distinguish this from sibling write tools like video_project_write 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?

Gives real preconditions: confirm with the user before calling, call video_guide first for the catalog and per-action schema, and asset deletion is refused unless force=true. It lacks an explicit statement of when NOT to delete versus an alternative (e.g. cancel_staged_changes), so it stops short of a 5.

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