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

Annotations already declare readOnlyHint/idempotentHint/non-destructive/openWorld=false, and the description adds context they cannot carry: pattern-based detection that may miss or over-match, determinism guarantee, no network, no stored state, plus hard limits (64 KB input, 1 s per call, 1 MB result). That is exactly the added behavioral value expected.

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?

Content is well front-loaded with labeled sections, but the same information is delivered twice (Spanish block then English block) and a third time via the pointer to inputSchema.description, roughly doubling the necessary length. Every sentence earns its place, yet the duplication does not.

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?

For a 3-parameter, read-only transform with an output schema, the description covers purpose, alternatives, safety profile, determinism and size/time limits — everything an agent needs before calling it. Return values need not be described since an output schema exists.

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 for `types` is fully documented in the schema, so the baseline of 3 applies. The description's enumeration of detectable data types loosely maps to the `types` values but never explains `style` (label vs mask) or how `types` narrows detection.

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 concrete verb+resource ('Enmascara datos personales y secretos en un texto') and enumerates exactly what is detected (emails, Luhn cards, IBANs, IPv4, JWTs, sk-/AKIA/ghp_/xox/AIza API keys, PEM keys). It explicitly separates itself from the nearest sibling by naming extract-emails as the tool for extracting rather than masking.

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?

Uses explicit 'Cuándo' / 'No para' sections: mask before logging or sending text to a model, and not for finding email-like addresses (route to extract-emails instead). Both the positive trigger and the exclusion are spelled out, leaving nothing to inference.

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