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

Annotations already declare destructiveHint=true, openWorldHint=true and non-idempotent, so the safety profile is carried by structured data. The description adds nothing beyond that: it never mentions that the tool consumes a room/garden image plus optional reference images, that it returns a newly generated image, or whether the input asset is preserved, which is the key behavioral question for a destructive open-world generation call.

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?

A single front-loaded sentence with no filler and the trigger condition stated first. It is efficient but also thin — the brevity comes at the cost of saying nothing about the image inputs or the result.

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 tool with five parameters, deeply nested image unions, an output schema and destructive/open-world annotations, one intent sentence is not enough. The agent is never told what must be supplied (an image), what the tool returns, or how this differs from the many other image-editing siblings, leaving real decision gaps even though the schema covers formats.

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 80% and the nested image properties carry detailed guidance (no local paths, pass base64 unchanged, do not ask for file metadata), so the schema does the heavy lifting. The description adds no parameter meaning at all and never signals that an image is effectively required despite zero formally required parameters.

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 frames the tool purely as a user-intent trigger ("weeds and debris removed so a garden looks neat") rather than stating what the tool actually does, e.g. that it produces a cleaned-up garden image. It does scope the resource (garden/outdoor area, weeds and debris) which distinguishes it loosely from make_grass_greener or render_exterior, but it never says the operation is an image transformation, so an agent must infer the core action from the name.

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?

"Use when the user wants weeds and debris removed" is an explicit, actionable trigger condition, which is the main thing an agent needs to route here. It stops short of naming when not to use it — nothing tells the agent to prefer declutter_room for indoor spaces or make_grass_greener for lawn-only requests.

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