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

With no annotations, the description carries the full burden and does well: it discloses the four returned representations and explicitly states the cost of 1 credit, which is the kind of operational context annotations would otherwise supply. It stops short of saying what happens with an unparseable number (error vs. null) or guaranteeing the operation is side-effect-free.

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?

One sentence, front-loaded with the transformation, then the outputs, then the cost. No redundant restatement of the title or parameter name.

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 single-parameter pure transformation with no output schema, the description covers input tolerance, all return fields, and pricing, which is nearly everything needed to call it correctly. The only gap is error/edge-case behavior for inputs that are not valid Argentine numbers.

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 already 100% with one documented parameter, so the baseline is 3, but the description adds real meaning by enumerating the tolerated input variants (leading 0, 15, +54, spaces, hyphens) beyond the schema's two examples. This tells the agent it need not pre-clean the number.

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?

Names a specific verb+resource (normalizar teléfono argentino) and immediately specifies both accepted input shapes (con 0, con 15, con +54, espacios o guiones) and the exact outputs (E.164, WhatsApp, nacional, celular/fijo). This is unmistakably distinct from the sibling validators (validar_cbu, validar_cuit) without needing their schemas.

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 phrase 'escrito de cualquier forma' tells the agent this tool absorbs messy input regardless of format, which implies when to reach for it, but there is no explicit when-to-use/when-not statement or named alternative. Guidance is implied rather than stated.

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