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

Annotations already disclose non-read-only, destructive, non-idempotent, open-world behavior. The description adds one genuinely useful behavioral fact — property and landscaping are preserved — but it never clarifies that the tool produces a new image rather than mutating the source, nor how the destructiveHint applies to an image edit. That is a meaningful gap given the destructive annotation.

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 beginning with the usage trigger, with no filler, hedging, or restatement of the title. Every clause earns its place by adding either a condition or a preservation guarantee.

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?

With five parameters, deeply nested image variants, and a declared output schema, the description covers only the when-to-use slice. It omits input handling expectations and does not mention that the user can steer the result via additional_instructions, leaving that to the schema. Adequate as a trigger statement, incomplete as a full operating brief.

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/reference-image alternatives are documented in detail within the schema itself, so the schema carries the parameter burden. The description adds no parameter meaning at all — nothing about reference images or additional_instructions — so it neither compensates nor detracts.

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 sentence names a concrete transformation (dull/cloudy sky changed to clear bright blue) and a scope constraint (preserving property and landscaping), which is more specific than the bare name 'set_sky_blue'. It implicitly separates the tool from siblings like make_grass_greener or render_exterior, but never names those alternatives explicitly, so differentiation is left to inference.

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 'Use when...' framing gives a clear triggering condition: the user wants an overcast sky replaced with blue. It stops short of stating when NOT to use it (e.g., when the user wants a full re-render or arbitrary sky replacement that would belong to custom_prompt), so there is no exclusion guidance.

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