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

Annotations already note readOnlyHint=false; the description adds the crucial side effect that the call consumes saldo and references consultar_precios for the fee. It also notes reconciliation against registered obligations, implying the tool may alter or match records, though it stops short of saying exactly what changes.

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?

Three short sentences: purpose, parameter instructions, and cost warning. No waste, and the load-bearing information is front-loaded.

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?

For a 2-parameter tool with an output schema, the description covers required input, optional input, and a cost side effect. It does not spell out return handling in prose, but that is covered by the output schema; the only minor gap is exact format requirements for xml/refs.

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?

With 0% schema coverage, the description is the only source of meaning for the two parameters. It explains that 'xml' is the CEP XML and 'refs' is optional references to reconcile, but it does not specify the expected format (e.g., XML encoding or how refs are delimited).

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 names the exact action: process a CEP (SPEI voucher) and reconcile it against registered obligations. This clearly separates it from invoice/company validation siblings and makes the tool's domain evident.

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?

It gives clear context: use when you have a CEP XML and want to reconcile it against obligations. It also warns that this is a paid SPEI service and points to consultar_precios for current pricing, though it does not explicitly state when-not-to-use or name an alternative reconciliation tool.

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