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

Annotations already establish readOnly, idempotent, closed-world, non-destructive behavior, so the bar is lower; the description still adds real value by disclosing the negative scope — no image content inspection, purely geometric/metadata validation. That prevents an agent from assuming it performs face detection or content checks. It stops short of describing what a result contains beyond that.

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 tight sentences with the purpose front-loaded and the scope limitation immediately following; no redundant restatement of the tool name. The dangling 'page_url' reference slightly undercuts an otherwise efficient structure.

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 six-parameter validation tool with no output schema, the description should indicate what comes back — per-criterion pass/fail, a list of violations, a boolean — and it does not. With half the parameters undocumented in the schema and the 'page_url' pointer left undefined, an agent knows the scope of the check but not how to interpret the result.

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?

With 50% schema coverage, the description partially compensates by naming the concepts being checked (aspect ratio, pixel limits, head height share, file size/format), which maps loosely to width_px/height_px, head_height_px, file_kb, and file_format. But head_height_px is already documented in the schema as 'Chin to crown in pixels,' and the description adds no format, unit, or constraint detail beyond it.

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 ('Check') and resource ('a photo's measurements against a spec') and enumerates the four criteria evaluated: aspect ratio, pixel limits, head height share, and file size/format. It is clearly distinct from get_photo_spec and list_photo_specs, which retrieve spec data rather than validate a photo, though it never names those siblings directly.

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 one explicit exclusion ('Does not look at the image itself; for a full check use the free checker at page_url'), which is genuine when-not guidance. However, 'page_url' is an unexplained dangling reference with no tool or location defined, and there is no guidance on when to supply the optional file_kb, file_format, or head_height_px parameters versus omitting them.

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