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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds what they do not: no network access, no stored state, determinism guarantee, and concrete limits (64 KB JSON input, 1 s per call, 1 MB result). This is exactly the operational context an agent needs before deciding whether a large input will fail.

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?

Sentences are short, labeled (When / Not for / Side effects / Deterministic / Limits) and front-loaded with the definition. The main cost is that the entire block is duplicated in Spanish and English, which doubles length while adding no information for a given reader.

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 pure-function hash tool with an output schema, rich annotations, and full schema descriptions, everything an agent needs is covered: purpose, exclusions, determinism, side effects, and size/time bounds. Nothing material is missing.

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%, so the three parameters are already fully documented in structured form; per the rubric this sets a baseline of 3. The description restates the accepted input encodings but says nothing about output_encoding (hex/base64/base64url) or how to pick it, so it does not exceed the baseline.

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 SHA3-384 digest (FIPS 202)") plus the accepted input forms (text, hex, base64). It also names the exact sibling it must not be confused with (hash-sha384), so the agent can discriminate among the many hash-* tools without opening schemas.

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: an exact digest of given text or bytes is needed, e.g. to compare content or match a published checksum" gives concrete selection context, and "Not for: computing the SHA-384 digest (hash-sha384)" explicitly routes to the alternative. Both positive and negative guidance are present.

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