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

Annotations already establish readOnly/non-destructive, and the description adds information annotations cannot carry: that the tool neither requests nor returns personal data, that name/DNI/address/contact appear as bracketed gaps in the resulting document, and that the agent must not ask for or write such data in the call. That is exactly the kind of operational constraint that prevents a bad invocation.

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?

Front-loaded with what is returned, then the exclusivity rule, then the privacy constraint — the right order. The parenthetical clause about bracketed gaps is long but earns its length by preventing a specific error; no sentence is pure 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?

There is no output schema, so the description must sketch the return shape, and it does: entries carry identifier, purpose, and required data, plus nine grounds with their allegations. It does not specify the serialization or ordering, a minor gap for a zero-parameter read-only catalogue.

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 zero parameters the baseline is 4, and the description correctly avoids inventing inputs. It does add meaning about the values the agent will later choose (`tipo`, `motivos`) and clarifies they are catalogue outputs rather than call arguments, though a hurried agent could momentarily mistake them for parameters.

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 two precisely identified resources: the letters composing `carta_deudas` (with identifier, purpose, and required data) and the nine opposition grounds to the monitorio with what each alleges. It anchors itself against the sibling `carta_deudas`, so an agent can tell catalogue from generator without opening a schema.

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?

Explicitly directs usage: 'Es la única lista válida: úsala para elegir el `tipo` y los `motivos`, y no inventes ninguno', which tells the agent both the task and the failure mode to avoid. It stops short of naming a competing tool to prefer in a specific scenario, but the exclusivity claim covers the practical alternative.

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