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

Annotations only say readOnly=false, destructive=true, openWorld=true; the description goes well beyond that by disclosing credit cost and the refund-to-actual-usage behavior, the plan requirement, and the crucial output semantics (result is a NEW file, the original stays in storage). That mutation/side-effect profile is exactly what an agent needs before invoking a destructive write.

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?

It is a dense paragraph rather than skimmable lines, but the ordering is sound — action, modes, cost, mask inputs, output — and each clause carries information (mode semantics, defaulting, coordinate convention). Slightly long, but nothing is filler.

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 an 8-parameter, nested-object, mutation tool with no output schema, the description covers the essentials: coordinate conventions, mask semantics, cost/refund, plan prerequisite, and where the result lands. It does not address failure modes (e.g., missing plan, model rejection) or timeout/latency expectations, which would complete the 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?

With only 50% schema description coverage, the description usefully compensates: it explains `region` as a rectangle in 0–1 fractions measured from the top-left, defines `maskUrl` as a same-size PNG transparent where change should occur, and clarifies `prompt` is required for `fill`. `url`, `slot`, and `expandPercent` are left to the schema, so it is good but not fully compensating.

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 names a specific verb (edit part of a picture with AI) and enumerates the three concrete modes it supports — `fill`, `erase`, `expand` — each with a one-line semantic gloss. An agent can immediately distinguish this from uichemy_crop_image (a mechanical crop) and from uichemy_upload_image or uichemy_set_image_display without opening either 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?

It clearly states the conditions for each mode (paint something new, remove the area, extend outward) and the prerequisite plan, which is genuine when-to-use guidance. What it lacks is an explicit exclusion or routing statement — it says 'same write as uichemy_crop_image' but never tells the agent when to pick crop_image versus this tool.

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