edit_with_agent

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

With no annotations, the description carries the disclosure burden. It transparently describes the agent's autonomy—selecting objects, planning, applying, verifying, and revising—and states the return value. It does not mention persistence, undoability, or cost/time, but the core behavioral cycle is well covered.

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?

Three sentences, each earning its place: a front-loaded statement of what the tool does, a conditional parameter explanation, and the return summary. There is no filler or repetition of the schema.

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 complex agent tool with no output schema and no annotations, it provides the essential invocation context: required instruction, optional scene_path behavior, workflow, and return value. It leaves minor gaps around persistence and relationship to save_scene/undo, but nothing that blocks a competent agent from calling it 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?

Schema description coverage is 0%, so the description must compensate. It meaningfully explains the scene_path option and its default behavior. The required instruction parameter is only described as 'one instruction,' leaving exact format and example unstated, though context makes it reasonably inferable.

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 a specific action—'Run the full editing agent on one instruction'—and enumerates the agent's pipeline (segment, plan, edit, verify, revise). This makes it unmistakably distinct from the granular sibling tools like add_object or segment_scene.

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 gives clear conditional usage for scene_path ('pass to load... or omit to act on the loaded scene'), which is useful. However, it does not explicitly state when an agent should choose this full-agent tool over the individual sibling operations, or when the granular tools are preferable.

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