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

Annotations only say readOnly/openWorld; the description adds substantially more: a 3-calls-per-day free quota, the exact paid fallback ($0.0015 USDC via x402 or card credits) and where payment is passed (params._meta['x402/payment']). It also discloses that encoding is computed locally with nothing stored and that output is UTF-8 byte mode, which an agent needs to reason about cost and side effects.

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?

Billing/quota is front-loaded before the capability statement, which is the right priority order, and the whole thing is three dense sentences. The closing 'When to use' sentence partly re-lists the content types already enumerated, a small redundancy that keeps it from a 5.

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 the description needn't explain return values, yet it still sketches the SVG/GIF shapes usefully, and it covers cost, privacy and every parameter family. The one gap is that all 11 params are optional and nothing says what happens if no content parameter is supplied.

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 the baseline is 3, but the description adds genuine semantics the schema doesn't: that ssid+password map to a WIFI: QR, that payment URIs like ethereum:/USDC are a supported content type, and how ecc/scale/margin/colours/matrix shape the rendered image. It doesn't tie every parameter to an effect, so not 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 a specific verb+resource ('QR code generator') and enumerates the input classes it accepts (text, URL, payment URI, Wi-Fi credentials) plus the output forms (SVG inline/data URI, GIF data URI). No sibling tool overlaps with QR generation, so the agent can select it unambiguously from the list.

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?

An explicit 'When to use:' sentence names the trigger scenarios — URL, payment request, Wi-Fi login, any text — which is clear positive guidance. It stops short of exclusions or named alternatives, but none of the siblings are plausible substitutes, so the missing exclusion costs little.

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