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

Given readOnlyHint=true and openWorldHint=true, the description still adds substantial non-obvious behavior: only the first 256 KB is read (a truncation limit that can silently affect results), a non-image returns 415, an EXIF-less image returns 200 with hasExif=false, and billing is per successful call at $0.002 in USDC via x402 with failed calls free. These are exactly the operational details annotations cannot convey.

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 front-loaded with the extracted field list and then layers in format, read limit, error semantics and pricing – every clause carries information. It is a dense multi-clause run-on rather than clearly segmented sentences, which slightly hurts scannability, but 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?

With an output schema present, return-value structure need not be explained, and the description covers everything else an agent needs: accepted input formats, the 256 KB truncation limit, both failure-mode semantics, and the payment model. Nothing required to invoke it correctly 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 description coverage is 100% for the single url parameter, so the schema already defines the format and expected image types; baseline is 3. The description adds only the 256 KB partial-read behavior relevant to that URL, which is useful but marginal against what the schema supplies.

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 opens with a specific, concrete enumeration of what is extracted (make/model, lens, date, exposure, GPS) and the exact source (EXIF of a JPEG/HEIC/TIFF/PNG at a URL), which clearly separates it from generic image tools like image, describe_image, or ocr. It never names a sibling tool, so it stops short of the explicit differentiation a 5 requires.

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 only implied through format constraints, not stated as guidance. There is no 'use this instead of image/describe_image/ocr when you need raw camera metadata', and no statement of when EXIF extraction is inappropriate. The format list lets an agent infer applicability, but alternatives are left to inference.

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