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

Annotations already declare readOnly, idempotent, non-destructive and openWorld=false, so the safety profile is covered. The description still adds real value beyond them: deterministic output, no network or stored state, the link-scheme allowlist, and concrete limits (64 KB JSON input, 1 s per call, 1 MB result) that an agent must respect to avoid failures.

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 core Spanish sentence is well front-loaded, but the description is then duplicated almost verbatim in English and closes with a self-referential pointer ('[EN completo / full EN: inputSchema.description]') that points at text the agent already has in the schema. Roughly half the token budget is redundant repetition.

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-value description is not required, and the remaining gaps an agent would care about — determinism, limits, escaping/allowlist behavior, absence of side effects — are all covered. The only shortfall is that the misleading generic 'when' list invites misuse of the tool on inputs (headers, tokens, IP ranges) it does nothing for.

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?

Only one parameter, and schema description coverage is 100%, so the schema already carries the required/type contract (baseline 3). The description does add useful input semantics by enumerating the supported Markdown constructs (headings, tables, blockquotes, images, fenced code), which tells the agent what the renderer will and will not interpret, but it offers nothing on formats or edge cases beyond that.

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 resource ('Convierte un subconjunto de Markdown a HTML seguro') and enumerates the supported subset, plus the security behavior (raw HTML escaped, link scheme allowlist). It also names the sibling it is not ('markdown-to-text'), so an agent can separate it from the other markdown-* tools.

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 exclusion is explicit and useful ('No para: eliminar la sintaxis Markdown (markdown-to-text)'), which is the strongest routing signal. However, the 'Cuándo' clause lists a grab-bag of unrelated triggers (HTTP header, token, version, IP range, agent-readiness file) that reads like boilerplate reused across many sibling tools and does not actually describe when one would render Markdown to HTML, muddying rather than sharpening selection.

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