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

Annotations already declare read-only, idempotent, closed-world and non-destructive, but the description still adds value the structured data cannot: deterministic output, no network access, no persisted state, and concrete operational limits (64 KB input, 1 s per call, 1 MB result). It also discloses semantics beyond stripping — link and image text are preserved.

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?

Front-loaded and well ordered (purpose → when → not-for → side effects → limits), but the full English block duplicates the Spanish text verbatim, and that same English block is repeated again inside the input schema description. Roughly half the content is redundant restatement rather than new information.

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 explanation is unnecessary, and the description covers safety profile, determinism, limits and the sibling alternative. The one loose end is the size-ceiling discrepancy (64 KB stated vs. 1 MB maxLength in schema), which an agent could trip over on large inputs.

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 required parameter at 100% schema coverage (including an example and maxLength), the schema carries the baseline. The description adds content-level meaning by specifying what survives the transformation (link/image text kept), which affects what the caller should send. Minor tension: the description says 64 KB input while the schema allows maxLength 1048576 characters.

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 ('Elimina la sintaxis Markdown … devuelve texto plano') and enumerates exactly which constructs are stripped (headings, emphasis, links, lists, tables, code fences). It also distinguishes itself from the nearest sibling by name (html-to-text), so the agent can separate the two without inspecting 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 'Cuándo' clause gives concrete trigger cases (URL, HTTP header, token, version string, IP range, HTML/Markdown document, agent-readiness file that must be parsed, built or checked exactly). The 'No para' clause names the exclusive alternative html-to-text and the condition that selects it, so routing is unambiguous.

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