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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantive behavioral context beyond them: per-format size ceilings, the SVG-only bulk endpoint with item/count limits, the warning that EAN/UPC output is format-valid only and not GS1 registration, and an explicit non-guarantee of scannability due to contrast, print size, quiet zone and reader. That is unusually rich disclosure for a generator.

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?

Four dense sentences with zero filler, front-loaded with the core output formats and size limits, then constraints, then caveats. Each sentence adds distinct information an agent needs.

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 no output schema and 8 optional parameters, the description still conveys the return shape (SVG markup, PNG base64, or data URL) and the salient limits. The main gap is the relationship between data and payload and the defaults for bg/fg/ecc/margin, which an agent must guess.

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 0% across 8 parameters, so the description must compensate; it explains the format parameter's three values and the size ceiling that varies by format, which is genuinely useful. But bg, fg, ecc, margin and the data-vs-payload distinction (mutually exclusive? which wins?) are never addressed, leaving over half the parameters undocumented anywhere.

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 and resource ('Generate a static QR code') and immediately narrows scope: SVG default up to 2000 px, PNG base64 or data URL up to 1024 px, from data or a payload object. The 'static codes only: no redirects, no dynamic/editable codes, no scan analytics' clause cleanly separates it from dynamic-QR style siblings, though it never names qr_payload_build, qr_inspect or barcode_generate 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?

Gives explicit when-not conditions (no redirects, no dynamic/editable codes, no analytics) and notes the bulk path with its own limits (SVG-only, ≤50, ≤256 bytes per item). It does not tell the agent when to prefer qr_payload_build to construct a payload first or qr_inspect to verify output, so routing against siblings is only partially solved.

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