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

Annotations already declare read-only, no-network and idempotent, yet the description adds real value on top: explicit limits (JSON input up to 64 KB, 1 s per call, result up to 1 MB) and the fact the digest is unkeyed. Minor ding: the stated 64 KB input cap conflicts with the schema's maxLength of 1,048,576 characters, and "solo lectura, sin red" largely restates the annotations.

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?

Each language block is front-loaded with the operation, then when/when-not, then side effects and limits – no filler sentences. The bilingual duplication doubles the length, but that appears intentional for a Spanish/English service rather than padding.

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?

Output schema exists so return values needn't be explained, and annotations cover the safety profile; the description fills in determinism, limits, and the sibling exclusion. The only gap is the 64 KB limit conflicting with the schema's 1 MB maxLength, which could confuse an agent about truncation 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 description coverage is 100%, so the three parameters (data, input_encoding, output_encoding) are already documented with enums and defaults. The description only implies byte-vs-text input via "texto o de unos bytes" and never explains how hex/base64 input or hex/base64url output encoding are selected, so this is baseline 3.

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 (computes the BLAKE2s digest with 256-bit output, RFC 7693, unkeyed), which pins the exact algorithm variant. It immediately disambiguates from the closest sibling by naming hash-sha256 as out of scope.

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?

"When" gives a concrete use case (compare content, match a published checksum) and "Not for" names one alternative explicitly. However, the sibling list contains ~20 other hash tools (hash-blake2b512, hash-sha3-256, hash-shake128, hash-multi), and the description only routes away from SHA-256, leaving the rest to inference.

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