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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, yet the description still adds real context: no network access, no stored state, determinism, and per-call limits (1 s, 1 MB result). One flaw: it claims 'JSON input up to 64 KB' while the schema's data maxLength permits 1 MB, so the stated limit conflicts with the structured constraint.

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 version is tightly front-loaded with purpose, then usage, then side effects, then limits. The cost is that the entire content is duplicated in Spanish and English, roughly doubling length without added information per 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?

With a rich annotation set and an output schema present, return format needn't be explained, and the description covers purpose, routing, safety, and limits. The one gap is the input-size limit that disagrees with the schema's maxLength, which could mislead an agent on large inputs.

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% with enums documented for both encoding parameters, so the baseline is 3. The description mentions text/hex/base64 input but adds no syntax or format detail beyond the schema and says nothing about output_encoding values.

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 SHA3-512 digest (FIPS 202) of text, hex or base64 input') and names the exact sibling it is not (hash-sha512). An agent can distinguish it from hash-sha512, hash-sha3-256, and hash-sha3-384 without opening any 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?

Explicit 'When' clause (need an exact digest to compare content or match a published checksum) and an explicit 'Not for' clause routing to hash-sha512. This is the when/when-not/alternative pattern at full strength.

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