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

Annotations already indicate a non-read-only, non-idempotent operation. The description adds context about the 'persistent editable project' and 'real HyperFrames project workspace,' reinforcing the stateful effect. But it does not disclose whether this agent run is asynchronous, requires follow-up approval/status, or how changes are surfaced, so there is meaningful depth it still omits.

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 one sentence, compact, and directly communicates the core capability without fluff. It is easy to parse and front-loads the most important semantic content, though it also spends some space on 'real HyperFrames workspace' phrasing that adds marginal clarity.

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?

The tool has no output schema and a low-detail input schema, so the description needs to explain more about the full operation. It omits important workflow context—there is no mention of return value, run lifecycle, approval status, or the relationship to get_editor_run/approve_editor_run/cancel_editor_run. This makes the tool difficult to coordinate correctly.

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 input schema provides no descriptions for project_id or prompt and schema description coverage is 0%. The description only hints at them by saying 'tell your agent...' and mentions 'project workspace,' but it never explicitly explains what the prompt or project_id should contain, how they relate, or how they should be used. This fails to compensate 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?

Description uses a specific verb+resource pattern: 'build or revise the persistent editable project,' and lists concrete authoring targets such as scenes, layers, variables, files, motion, and narration plans. It clearly separates this tool from sibling actions like create_editor_project, render_editor_project, and get_editor_run.

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 implies the tool is for instructing the Editor agent to build or revise a persistent project, which gives some usage context. However, it does not explicitly state when to avoid it or which sibling tools to use instead, such as create_editor_project for initial creation or approve_editor_run for approval flow.

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