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

Annotations already declare readOnly, non-destructive, idempotent and closed-world, so repeating "sin efectos secundarios / determinista" earns no credit. What does add value is the caveat that cédulas have no check digit and validity cannot be confirmed offline, plus concrete operational limits (64 KB input, 1 s per call, 1 MB result) that the annotations do not carry.

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?

The content is front-loaded well, but the entire text is duplicated in Spanish and English, roughly doubling length for the same information, and the side-effects/determinism sentences only restate annotations. The generic Colombian-rules enumeration is filler for this particular tool.

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?

An output schema exists so return values need not be explained, and the description covers syntax rules, the no-check-digit limitation, determinism and resource limits. The one real gap is input normalization behavior (prefixes, dots, whitespace) given the schema's contradictory example.

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 one parameter and 100% schema coverage the baseline is 3, but the description supplies constraints the schema lacks: digits only, 3-10 digits, no leading zero. It does not resolve the mismatch between the schema example "CC 1.020.304.050" (which carries a prefix and dots) and the stated digits-only rule, leaving ambiguity about whether such input is accepted or normalized.

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 ("Verifica la SINTAXIS ... y la formatea con puntos") plus the resource and the acceptance range (3-10 digits, no leading zero), which is enough to distinguish it from the co-nit sibling it explicitly names. An agent knows exactly what it gets without opening the 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?

The "Cuándo / Not for: computing the DIAN verification digit (co-nit)" pair gives an explicit exclusion and names the alternative, which is the main routing risk. The positive "when" clause, however, is generic family-level boilerplate (DIAN, Ley Emiliani, COP, IVA, GMF, UVT) that has little to do with formatting a cédula, so it guides less than it appears to.

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