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

Annotations already declare readOnly and non-destructive, and the description adds substantial behavioral context beyond them: per-call price ($0.0045 USDC), payment mechanism (x402 on Base/Solana/Polygon/Arbitrum), automatic payment by x402 clients, EXIF auto-rotation, and a free sample call. The paid, in-call settlement requirement is a critical trait an agent must know before invoking.

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?

Purpose is front-loaded, then use cases, params, pricing, and a sample call. The pricing/payment sentence is lengthy but earns its place given the pay-per-call model. Slightly dense overall but 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?

Covers formats, dimensions caps, use cases, and the payment model well for a tool with no output schema. The one gap is the return format (base64 vs URL, single vs batch), which an agent would want to know, though it's a minor omission given the otherwise thorough coverage.

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 only 29%, so the description must compensate, and it does: it summarizes every parameter with defaults and bounds and critically states that image_base64 or image_url is 'one required' — important since the schema marks zero required params. It doesn't explain the semantics of the fit modes (cover/contain/fill), which keeps it from a 5.

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 specific verbs and resource: 'Resize, crop-fit and convert images', enumerating input formats (PNG, JPEG, WebP, AVIF, GIF, TIFF, SVG) and output targets (webp, png, jpeg, avif). This clearly distinguishes it from siblings like image_alt_text, screenshot, and ocr, which have different jobs.

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?

Provides explicit use cases: shrink screenshots before sending to a vision model, create thumbnails, or convert formats. This gives strong context for when to reach for the tool, though it names no alternative tool or when-not-to-use condition.

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