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

Read-only status is already covered by readOnlyHint, but the description adds important behavior: the seven-rule classifier, the exact return contents, the unit flexibility, the flipping behavior on borderline faces, and the lack of any accuracy claim. These are real behavioral traits beyond the annotations and are highly useful for trust calibration.

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 sentences, each earning its place: what it does, what it returns, what it is not, and the accuracy caveat. The information is front-loaded and there is no filler.

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 read-only, four-parameter computation tool with full schema coverage and no output schema, the description covers inputs, outputs, limitations, unit handling, and the photo alternative. Nothing essential for correct invocation is missing.

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 all four parameters are fully documented. The description adds only unit flexibility ('any consistent unit') and reinforces that the inputs are distances. That is useful but the schema already carries the semantics, so the baseline of 3 fits.

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 states a specific verb (classify) and resource (face shape), names the exact inputs (four distances) and outputs (shape, matched rule, four ratios), and distinguishes itself from its siblings by naming get_embed_snippet and the site for photo-measurement. An agent can see immediately what this does and what it does not.

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?

It clearly says when to use this tool: when you already have four distances. It rules out photos and points to get_embed_snippet or the site. There is no explicit exclusion against other computation tools, but the input requirement is a strong and clear usage condition.

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