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

Annotations cover the safety profile (readOnly false, idempotent false, non-destructive), and the description adds real behavior beyond them: a hard precondition that the description must contain exactly one item with explicit colour, an instruction to prompt the user rather than invent a colour, the menswear/womenswear override semantics, the returned review link, and the disclosure that a new item's image may still be generating in the background.

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?

Front-loads purpose and the primary alternative before the conditional detail, and every sentence carries a distinct rule. It is on the long side and the colour/exactly-one-item constraint is repeated from the schema description, which is mild redundancy rather than waste.

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 mutation tool with an output schema, the description covers preconditions, sibling routing, override semantics, and a hint about the returned review link and background image generation. An agent has everything needed to decide and call correctly.

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%, and both schema properties already carry detailed descriptions (10–150 chars, exactly one item, colour required, override of profile preference). The description restates that content rather than adding syntax or format detail beyond it, so the baseline 3 applies.

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 ('Adds'), resource ('one item ... to their Able.Style wardrobe'), and the input source ('from a text description supplied by the user'). The scope is narrowed to exactly one owned item, which separates it from the by-id, from-image, and closet siblings.

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?

Explicit routing rules: use this when the user describes an item in words; use add_wardrobe_item_from_image when a photo/attachment/URL is the source; fall back to create_image_upload with purpose wardrobe_image_add if transfer is unavailable; use add-to-or-remove-from-wardrobe-by-id for items already returned by suggest-outfit-tool. It even names an anti-pattern (don't infer a description from an image) and a blocking precondition (ask for colour if missing).

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