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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so the description's 'sin efectos secundarios' partly repeats them. However it adds genuinely new behavioral facts: determinism (same input, same output), input cap of 64 KB, 1 s per-call budget, and 1 MB result ceiling, plus the concrete rendering rules (headings become bold lines, tables become code blocks, escaping required for MarkdownV2).

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 purpose is front-loaded and dense, but the block duplicates itself almost entirely in Spanish and English ('[EN completo / full EN: inputSchema.description]'), and the misdirecting 'Cuándo'/'When' sentence consumes real estate without earning it. Content that is wrong is worse than content that is absent.

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 and the two required parameters are fully documented, so the structural side is covered, and limits/timeouts are disclosed. What is missing is accurate use-case framing: the stated 'when' scenarios belong to other tools in this catalog, leaving the agent without a correct picture of when a chat-format conversion is the right call.

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% and the enum already constrains target, so baseline is 3. The description earns above baseline by explaining what each enum value actually produces — dialect syntax per app, mandatory backslash escaping for Telegram, entity escaping for Slack — which the enum values alone do not convey.

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 (convert Markdown to chat-app formatting) and enumerates the three targets with their dialect specifics (WhatsApp *bold*, Slack mrkdwn <url|text>, Telegram MarkdownV2 escaping). It also names the sibling it is not (markdown-to-text), so an agent can distinguish it without opening the 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?

The negative guidance is good: 'No para: eliminar la sintaxis Markdown (markdown-to-text)' correctly routes the stripping case to the sibling. But the positive 'Cuándo' clause is wrong: it says to use this when a URL, HTTP header, token, version string or IP range has to be parsed or checked exactly, none of which this tool does. That actively misroutes an agent toward this tool for url-parse or http-headers-parse style tasks.

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