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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, and the description still adds real information: string-processing rather than a full HTML parser, determinism, script/style dropping, and explicit time and result-size limits. The stated '64 KB' input limit conflicts with the schema's maxLength of 262144, which is a mild self-inconsistency rather than an annotation contradiction.

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?

Purpose is front-loaded in the first clause and the when/not-for/effects/limits blocks are skimmable. The generic 'Cuándo' enumeration of unrelated artifacts (IP ranges, versions, tokens) is filler that dilutes the signal and could have been one short sentence.

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 a rich output schema and full annotations, the remaining essentials — processing model, determinism, limits, scope exclusions — are all covered. The only real completeness defect is the input-size figure disagreeing with the schema's maxLength, which could mislead an agent about acceptable payload size.

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 description coverage is 100%, so both parameters (html, escape) are already documented, including escape's default and the specific characters it affects. The description adds nothing about parameters — notably it never mentions escape or when to disable it — so the 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?

States a specific verb and resource ('Convierte HTML en Markdown (GFM)') and enumerates exactly which constructs are handled (headings, tables, fenced code with language, entity decoding, script/style removal). It also names the nearest sibling it is not ('No para: ... html-to-text'), so an agent can discriminate without opening a 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?

There is an explicit exclusion clause routing plain-text extraction to html-to-text, which is genuinely useful routing. However the 'Cuándo' clause is largely generic boilerplate (URLs, HTTP headers, tokens, IP ranges) that is not specific to HTML→Markdown and reads like a shared template rather than real selection guidance.

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