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

Annotations already declare readOnly/idempotent/non-destructive, and the description reinforces rather than merely repeats them by adding determinism, no-network, no-stored-state, and per-call limits (1 s, result ≤ 1 MB). The one flaw is the stated 'JSON input up to 64 KB' limit, which conflicts with the schema's maxLength of 1048576, so the operational bound is ambiguous.

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?

Front-loaded with the verb and algorithm, then labelled When / Not for / Side effects / Deterministic / Limits — easy to scan. However, the full text is duplicated in Spanish and English, roughly doubling length without adding information for an agent consuming one language.

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?

An output schema exists, so return-value explanation is not required, and the type, determinism, and cost limits are all stated — enough for correct invocation. The only gap is the unresolved 64 KB vs 1 MB input-size discrepancy, which could make an agent truncate or reject valid payloads.

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 parameters (data, seed, input_encoding) are fully documented in the schema itself and a baseline 3 applies. The description only restates that the seed is optional and 32-bit, and never mentions input_encoding (utf8/hex/base64), which is the parameter most likely to cause a wrong call.

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+algorithm: computes MurmurHash3 x86_32 with optional seed, and immediately qualifies it as non-cryptographic. It also names the closest sibling (checksum-xxh32) so the agent can distinguish it from the other ~20 checksum/hash tools without opening the 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 (fast non-cryptographic checksum for error detection, sharding, hash tables) plus an explicit 'Not for' clause naming the alternative checksum-xxh32 and its condition. This is the exact when/when-not/alternative structure the rubric rewards.

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