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

Annotations already establish a safe, non-destructive read profile, and the description layers on non-schema behavior: a hard 16 MP ceiling and a per-call cost of $0.003 USDC settled via x402, which tells the agent payment is required before invoking. It still omits whether the source image is unmodified and what the response contains (URL vs base64), so it is good rather than complete.

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-loaded with the capability list, then two compact operational facts (16 MP limit, $0.003/call). No filler sentences, though the parenthetical about resizing is doing double duty as the only semantic detail on a 9-parameter tool.

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 9-parameter tool with 44% schema coverage, no output schema, and zero required parameters, the description is under-specified: it never says what happens if no operation is supplied, what the return payload looks like, or how the URL/base64 inputs interact. The cost and size constraints are useful additions, but key call-shaping details are 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 44%, so several parameters (width, height, image_url, image_base64) carry no description anywhere. The description partially compensates by clarifying that resize means fit-inside-a-box and that input comes from a URL or base64, but it says nothing about aspect-ratio behavior, crop coordinate space, default format, or whether URL and base64 are mutually exclusive.

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 names specific operations (resize/fit, crop, rotate, grayscale, convert/compress) against a specific resource (PNG/JPEG images from URL or base64), so an agent knows exactly what the tool does. It does not, however, distinguish itself from close siblings such as image_convert, image_fast, or image_pro, leaving the agent to guess which of the near-identical image tools applies.

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?

Usage is implied by the capability list, and the pricing/size caps hint at when the tool is economical, but there is no explicit when-to-use or when-not-to-use guidance. With siblings like image_convert and image_fast overlapping directly on convert/compress, the absence of routing guidance is a real gap.

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