vizcom_edit_region

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

Against annotations that only declare non-read-only, non-idempotent, open-world behavior, the description adds real substance: it discloses credit consumption, asynchronous behavior via a returned prompt id, and the important caveat that the model may alter unselected areas despite the mask. The only modest gap is it does not state any preconditions such as ownership or model availability.

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?

Four short sentences, each carrying distinct information (core action, mask constraint, model caveat, cost and polling), with no filler or repetition. The core action is front-loaded and constraints follow in priority order.

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 mutating, async tool with no output schema, the description covers cost, the returned prompt id, and the masking contract well enough to call it correctly. The remaining gap is that the drawingId and prompt parameters are never characterized, which matters given 0% schema coverage.

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?

With schema description coverage at 0%, the description must carry parameter meaning, and it does partially: it explains that the source and mask are PNGs with matching dimensions and defines the white/black mask convention. However, it says nothing about the drawingId (target UUID) or the prompt's length limits and role, leaving half the parameters undocumented anywhere.

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?

"Submit one masked local edit" gives a specific verb (submit) and resource (masked local edit) that clearly separates it from read-side siblings like vizcom_get_result or vizcom_status. It never names the related sibling vizcom_make_region_mask, so the mask-creation step is only implied rather than contrasted explicitly.

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 workflow (submit, then poll the returned prompt id, review output) but gives no explicit when-to-use or when-not guidance versus siblings such as vizcom_render_sketch or vizcom_make_region_mask. An agent must infer that a mask must be produced first and that this is the edit path rather than the generation path.

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