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

Annotations already cover read-only, idempotent, non-destructive and closed-world, so the bar is lower; the description still adds real value with "sin conexión" (no network), "sin estado guardado", determinism, and concrete limits (64 KB input, 1 s per call, 1 MB result). The caveat "Son heurísticas, no un veredicto" correctly warns that output is probabilistic rather than a security decision.

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 front-loaded Spanish sentence is dense and useful, but the bilingual duplication (EN block repeats the same content) and the copy-pasted "Cuándo" enumeration of unrelated artifact types pad the description without adding information for this 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-shape explanation is rightly omitted, and the "not a verdict" caveat is a valuable completeness touch. Still, the misleading usage clause leaves the agent unsure whether this tool consumes headers/documents, and there is no indication of what kind of signal categories or severity framing the result carries.

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 a single parameter at 100% schema description coverage, the schema already documents the required `url` string with a 4096-char bound and an example. The description adds no further semantics about the input (e.g. whether scheme is required, how relative URLs are handled), so baseline 3 applies.

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 ("Señala indicios de phishing en una URL") and enumerates the exact signals detected (punycode/homógrafos, host IP, «@», acortadores, TLD, subdominios, lure words), which is far more concrete than the title. However, the purpose is slightly blurred by the generic "Cuándo" list that describes parsing HTTP headers, tokens, IP ranges and agent files — tasks this tool cannot perform.

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 does name an alternative and an exclusion ("No para: analizar una URL absoluta (url-parse)"), which is genuinely useful routing. But the "Cuándo" clause is boilerplate shared with other server tools and does not describe this tool's real trigger condition (suspicious link triage / pre-click vetting), so an agent gets a partially misleading usage signal.

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