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

Adds real value beyond annotations: rejects anchors, aliases, tags, merge keys and multi-documents, is deterministic, and declares hard limits (1 s per call, 1 MB result). Annotations already cover readOnly/idempotent/no-network, so this is well above the bar, but the phrase 'entrada JSON de hasta 64 KB' is an error — the input is YAML and the schema permits up to 1 MB, which could mislead on size limits.

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 content is front-loaded and each clause is informative, but the entire description is duplicated in Spanish and English, and the tail sentence '[EN completo / full EN: inputSchema.description]' points at text it already repeated. Roughly half the text is redundant.

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 values need no explanation; the description covers accepted input, rejected constructs, side effects, determinism, and limits — everything needed to invoke a single-parameter parser correctly. Only the mistranslated size limit is a blemish.

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% with an example, so baseline is 3; the description goes further by enumerating the accepted YAML subset (block maps/sequences, flow collections, | and > blocks, comments), which tells the agent what input will actually succeed. No syntax details for quoting edge cases, keeping it below 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 specific verb and resource ('Convierte un subconjunto seguro de YAML a JSON') and enumerates exactly which YAML constructs are supported and which are rejected. It names the sibling yaml-build as the inverse operation, so an agent can distinguish the two 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?

Explicit 'Cuándo:' clause lists the triggering scenarios (transform, compare, or check structured data exactly) and 'No para:' names the alternative tool (yaml-build) for the opposite direction. Both when-to-use and when-not-to-use are covered.

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