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

Annotations only say readOnly/openWorld; the description adds real behavioral context beyond them: first read is slow and later reads are cached, do not retry on slowness, oversized ranges get truncated and reported, and some PDFs are image scans with no text (in which case the link is returned). It also states a citation policy distinguishing citable modes (`pagina`, `desde`/`hasta`) from the non-citable `buscar` context.

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 mode list and the three ⚠️ blocks are front-loaded and each carries actionable content. The opening sentence's long enumeration of ~30 regulators is heavy, though it does establish scope; a grouped phrasing would have preserved the meaning at a fraction of the length.

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?

With 7 optional params, no output schema, and a document corpus that can exceed a hundred pages, the description covers the failure modes an agent would otherwise hit: scan-only PDFs, truncation, latency, and citation validity. Nothing needed to call it correctly or to interpret the result appears to be missing.

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 100%, so per-parameter meaning is already documented; the description nevertheless adds the mode model that the flat schema cannot express (which combination of optional params yields ficha vs. outline vs. range, and that `buscar` returns locating context only). It stops short of stating precedence when conflicting modes are combined (e.g., `pagina` plus `desde`), which keeps it off a 5.

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 concrete verb and resource (leer el texto de una norma, por páginas, extraído del PDF) and enumerates the covered regulators, so the agent knows exactly what corpus this tool serves. It also names the sibling that supplies the required `clave` (buscar_normas_reguladores), making the pairing unmistakable.

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 defines six modes and the argument combination that selects each (no args = ficha, `estructura`, `articulo`, `buscar`, `desde`/`hasta`, `pagina`), plus a strong when-not: do not read a 100+ page regulation end to end. It also routes the agent forward ('Se pide con la `clave` que devuelve buscar_normas_reguladores'), which is exactly the alternative-selection guidance this dimension rewards.

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