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

The description goes well beyond the annotations (which only indicate destructiveHint: true) by clarifying that the action is scoped to the explicit project_id, creates a new version so prior cuts remain recoverable in version history, and drops all current edits. It also instructs the agent to state honestly when it chose to rebuild from source, adding useful behavioral guidance.

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 front-loaded with the PROJECT-SCOPED note and provides essential behavioral details in three sentences. The final instruction about 'state honestly' is somewhat tangential to tool mechanics, but it does not detract significantly. Overall it is efficient and well organized.

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 action with a single parameter, the description covers scope, behavior, recoverability, and return value adequately. It does not mention error conditions or what happens if the project is not found, but those are likely handled elsewhere. The absence of an output schema is mitigated by the mention of returning the project identity.

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?

The parameter project_id is already fully documented in the schema (coverage 100%) with clear instructions to copy it from list_projects/open_project/project_state and avoid guessing. The description adds only that the call is scoped to that id and returns the project identity, which is marginal and not parameter-specific.

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 resets the edit by starting again from the full untouched source video, dropping all cuts, captions, tracks, and effects. This is a specific verb (reset) on a well-defined resource (the edit/project), and it distinguishes itself from sibling removal tools by implying a full clean-slate operation rather than removing individual elements.

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 context that it should be used 'whenever that is the best route for the brief or current edit,' which gives a general sense but does not explicitly contrast with alternatives like the many remove_* tools. There is no explicit 'use this instead of X when Y' guidance, leaving some inference to the agent.

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