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

Annotations only declare that this is non-read-only and non-destructive; the description adds the crucial behavior that it returns credit cost and balance without charging and that no generation happens until confirm_look_generation. It also discloses the widget-only upload path and the saved-selfie default, which the agent could not infer from annotations or schema.

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?

Three front-loaded sentences with no repetition: purpose first, then parameter routing, then the widget constraint, then the no-charge guarantee. Every clause carries information the 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?

For a preparation step feeding a two-stage try-on flow, the description covers inputs, upload channel, defaults, and the fact that it returns cost/balance without side effects. An output schema exists and further detail on return shape is unnecessary.

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 coverage is 100%, so the schema documents each parameter, including the widget-set fields. The description still adds meaning the schema does not express, namely the mutual exclusivity of articleLookId and savedLookId ('Give one reference') and which selfie is used by default.

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 and resource: 'Prepare a try-on: BeautySpark recreates a makeup look on the user's selfie.' It also bounds the scope by saying nothing is generated until confirm_look_generation, which separates it from that sibling without needing the schema.

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?

Gives explicit prerequisites and alternatives: supply exactly one reference, articleLookId from find_article_looks or savedLookId from search_my_looks, and names both source tools. It also states what is not allowed (photos cannot come from chat attachments) and which selfie is defaulted.

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