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

Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds behavioral context beyond that by enumerating the detectable fashion categories and stating that output includes bounding box coordinates and confidence scores, which helps an agent judge whether the model fits the query. Operational details like image limits or multi-person handling are absent, keeping this below a 5.

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?

Two sentences with no filler: the first front-loads the verb and purpose, the second adds the usage scenario. The parenthetical category list is somewhat long but earns its place by communicating the detection taxonomy an agent needs.

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 an output schema present and 100% parameter coverage, the description's main job is usage context, which it largely delivers. The notable gap is input selection: all three image-source parameters are individually optional, and nothing states that exactly one image source must be provided, which an agent could misinterpret as allowing zero or multiple inputs.

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%, with each of the four parameters (image_url, threshold, image_path, image_base64) bearing its own description, so the description need not repeat parameter syntax. It adds a slight conceptual frame ('outfit image or photo', confidence) but no parameter-level guidance beyond what the schema already provides, matching the baseline of 3.

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 opens with a specific verb and resource ('Deconstruct an outfit image or photo into individual fashion pieces') and names concrete output categories (Upper-body garment, Lower-body garment, Dress, Footwear, Bag, Headwear) plus bounding boxes and confidence scores. It clearly communicates a detection/decomposition operation that differs from the sibling search and curation tools, though it never names a sibling 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 second sentence gives an explicit use case: 'Use this to break down full-body look photos and search for matching catalog items for each piece individually.' This provides clear context for when the tool applies, but it states no exclusions and names no alternatives, leaving the boundary with products.search.image_url and products.search.image_upload implicit.

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