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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the repeated 'solo lectura, sin red, sin estado guardado / determinista' lines add no new information. The description does contribute beyond annotations by stating the domain caveat that it never confirms a payment, and by giving operational limits (1 s per call, 1 MB result). The '64 KB input' limit sits oddly against the schema's 512-char payload cap, a minor internal inconsistency.

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?

Labels (Cuándo / No para / Efectos secundarios / Límites) give good front-loading, but the same content is presented twice (Spanish plus a full English restatement that also duplicates inputSchema.description). The money-math 'When' sentence earns no place in a QR parser definition.

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 a rich annotation set, a single fully documented parameter, and an output schema that carries the return shape, the description covers purpose, exclusions, side effects and limits adequately. The only substantive gap is that the usage trigger is boilerplate rather than QR-specific.

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% and the single parameter is fully documented, so baseline 3 applies. The description adds modest context by indicating the payload is a merchant-presented TLV string with templates, but adds no format or validation detail beyond what the schema already conveys.

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 opening sentence names a specific verb and resource (parse an EMVCo merchant-presented QR payload, TLV) and enumerates concrete sub-behaviors: CRC16 check, mandatory-field check, and labelling of Pix / EASPBV Bre-B templates. It also distinguishes itself from the closest sibling by stating it is format-check only and never confirms a payment, unlike br-pix-brcode which builds payloads.

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?

The 'No para: construir un BR Code Pix «copia e cola» (br-pix-brcode)' exclusion is an explicit, useful routing rule. However, the 'Cuando/When' clause is clearly boilerplate from a money-math tool ('un cálculo de dinero, impuestos o matemática financiera... redondeo, centavos, tasas'), which does not describe when to reach for a QR parser and could misroute an agent looking for rounding or rate math.

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