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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds that the output is a 'full hair profile' with nine classification types, which is useful but vague. It does not disclose operational details such as async polling or image requirements, but the schema already covers these, so the description adds marginal value beyond 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?

The description is padded with marketing phrases like 'Imagine having an AI hair expert in your pocket' and 'spot-on product recommendations,' which are irrelevant for an AI agent. It wastes tokens on hype instead of providing crisp, technical details. While it is only three sentences, the content is not efficiently structured for tool selection.

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?

Given the tool's complexity (oneOf request schema, polling parameter, async behavior), the description is incomplete. It explains the high-level purpose but omits usage context, such as requiring exactly three images (front, right, left) or that the tool is read-only and asynchronous. The output schema may cover return details, but the description still fails to provide a complete picture for an agent deciding to invoke it.

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?

The description does not explain the parameters at all. Schema coverage is 50%; the polling parameter is well-described in the schema, and the request object includes descriptions for src_file_urls and src_file_ids. The description's mention of 'ten unique curl shapes' refers to output, not input, so it fails to compensate for the 50% gap or add meaning to the parameters.

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 clearly conveys that the tool analyzes hair texture, thickness, and curl pattern to classify hair into nine types. It distinguishes from sibling hair tools (e.g., density, length, frizziness) by explicitly focusing on curl shape and type. However, the marketing tone obscures the direct imperative verb ('detect' or 'classify') and includes irrelevant brand messaging.

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 description provides no explicit guidance on when to use this tool versus alternatives like AI-Hair-Density-Detection or AI-Hair-Frizziness-Detection. It does not mention required inputs (three images) or any exclusions, leaving the agent without clear selection criteria.

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