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

Annotations already declare readOnlyHint, openWorldHint=false, idempotentHint and destructiveHint=false, so the safety profile is covered structurally. The description adds genuinely new operational context: no network access, no stored state, determinism, and hard limits (64 KB input, 1 s per call, 1 MB result). It also clarifies RFC semantics — Expires must be in the future relative to as_of and ideally under a year — which is behavior, not restated annotation.

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 RFC 9116 spec is well front-loaded, but the body then wastes space on off-topic boilerplate about URLs, tokens, IP ranges and HTML, and ends with a dangling placeholder '[EN completo / full EN: inputSchema.description]' that is a broken reference rather than content. The Spanish and English blocks largely duplicate each other, inflating length without adding 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 not required, and the description covers the validation rules, limits, determinism and the nearest sibling exclusion. The one gap is that the misleading 'when' list leaves an agent unsure whether this tool is scoped strictly to security.txt files or also to other parsed artifacts.

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 only two required params, so the baseline is 3. The description goes beyond the schema by explaining what as_of actually means functionally: it is the reference instant against which Expires is judged to be in the future, which the schema merely calls 'Reference instant ISO 8601'.

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?

The opening sentence names a specific verb and resource — 'Valida un security.txt según RFC 9116' — and enumerates the concrete checks (Contact and Expires required, known fields, https URIs, PGP signature). Combined with the explicit 'No para: ... (robots-txt-check)' exclusion, an agent can distinguish this from the closest sibling 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 'No para' clause is a genuine, useful exclusion that names robots-txt-check and the condition that selects it. However, the 'Cuándo' clause is generic template boilerplate ('una URL, una cabecera HTTP, un token, una versión, un rango de IP, un documento HTML o Markdown') that does not describe when to reach for security.txt validation and could mislead an agent into thinking this tool parses URLs, headers or HTML.

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