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

Annotations cover the mutation profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false), so the description is free to add operational context — and it does: Kling pre-validates photos and rejects unsuitable ones (e.g., AI-generated images), the call costs ~5 credits, and it returns an asynchronous job rather than the finished image. It stops short of naming the polling sibling (kling_get_task) or explaining result retrieval, but this is meaningful disclosure beyond the annotations.

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, front-loaded fragments: the action and input combinations come first, followed by validation behavior, cost, job model, and endpoint. The telegraphic 'a dress (dressInput), or a top (upperInput) and / or bottoms (lowerInput)' is dense but every clause carries information; little is wasted.

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 no output schema, the description covers cost, input validation behavior, the async job model, and the HTTP endpoint, which is close to what an agent needs to invoke and follow up correctly. It leaves the result-retrieval path only implied via 'A job, like kling_omni_image', which is a minor gap rather than a blocker.

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 100%, so all six parameters (including email and imageCount) are already documented in the schema; the baseline is 3. The description restates the dress-vs-upper/lower combination rule that dressInput's schema description also carries, adding readability rather than new semantics.

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?

States a specific verb+resource ('Dress the person in humanImage in clothes from images') and enumerates the exact input slots (dressInput, or upperInput/lowerInput), so an agent can immediately tell this is a garment-swap operation rather than image generation. The endpoint (POST /images/virtual-try-on) and the analogy to kling_omni_image further pin down its scope.

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?

Usage is implied through the input matrix (dress vs top/bottoms) and the note that Kling validates and refuses unsuitable photos, which hints at when the call will fail. But it never says when to prefer this over a sibling like kling_omni_image or kling_enhance_image, nor does it state exclusion conditions; kling_omni_image is cited only as a job-pattern analogue, not an alternative.

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