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

The read-only/no-network/no-stored-state line largely restates readOnlyHint and openWorldHint, so that part earns little. The genuinely additive content is the limits block (64 KB JSON input, 1 s per call, 1 MB result) and the determinism guarantee, which no annotation conveys and which an agent needs for batching and retry decisions.

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?

Within each language the text is front-loaded with the purpose, then When / Not for / Side effects / Deterministic / Limits in a scannable order, with no filler sentences. The full Spanish and English duplication roughly doubles the length for a single-language reader, which is a real cost even if intentional.

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 three-parameter pure computation with an output schema and full annotation coverage, the description covers everything an agent needs: what is computed, the exact formula, the disambiguating alternative, determinism, resource limits, and safety profile. Return values are correctly left to the output schema.

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 baseline is 3. The description earns a bump because the formula fixes the semantics the schema only labels: 'from' is the denominator under an absolute value and 'to' is the numerator, which resolves the sign behaviour for negative old values. 'decimals' is not mentioned in the description, keeping it short of a 5.

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 percentage change from an old value to a new value) and even gives the formula ((new − old) / |old| × 100) plus the absolute difference. It explicitly names the sibling it is not (percent-of), so the agent can separate it from the near-identical neighbour without opening either 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?

The 'When' clause gives the selecting condition (numeric result must be exact or reproducible rather than estimated), and the 'Not for' clause names the alternative tool (percent-of) with the exact scenario that routes there. Nothing about when to choose this versus percent-of or percent-ratio is left to inference.

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