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

Annotations already declare readOnlyHint/idempotentHint/openWorldHint=false, so the 'solo lectura, sin red' sentence is partly redundant. However the description adds genuinely new behavior: values are percent-decoded only when valid, the first occurrence of a duplicate name wins, output is deterministic, and there are explicit limits (64 KB input, 1 s per call, 1 MB result). Those are real operational constraints the annotations do not carry.

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 individual sentence is useful, but the entire description is duplicated verbatim in Spanish and English, and it closes with the meta-note '[EN completo / full EN: inputSchema.description]', which is artifact noise rather than agent-facing information. The generic 'When' enumeration also adds bulk without distinguishing this tool.

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?

This is a one-parameter, single-purpose tool with a full output schema, and the description covers scope, exclusion, determinism, and limits. What is missing is edge-case behavior for malformed input (e.g. a segment without '=', or invalid percent-escapes) since the 'valid' qualifier on percent-decoding implies but does not state fallback behavior.

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% and the single parameter is documented with an example, so the baseline is 3. The description goes beyond the schema by explaining how the string is interpreted (semicolon-delimited pairs, percent-decoding, duplicate-name resolution) and by stating the 64 KB ceiling, which clarifies the maxLength constraint in practical terms.

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 first sentence names the exact resource ('encabezado Cookie / Cookie request header') and the exact operation (parse 'name=value; …' into an object), including the subtle rule 'first occurrence wins'. It also explicitly names the sibling it is not ('set-cookie-parse'), so an agent can route between the two cookie tools 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?

The 'No para / Not for' clause is precise and actionable: it excludes Set-Cookie parsing and names the alternative tool that handles it. The positive 'When' clause is weaker because it is a generic template list ('una URL, una cabecera HTTP, un token… archivo para agentes') that is not specific to Cookie headers and reads as boilerplate shared across many sibling tools.

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