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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is structured data. The description still earns credit for information not in annotations: it uses its own parser with no eval, is deterministic, and documents hard limits (64 KB JSON input, 1 s per call, 1 MB result). It does not describe error behavior on invalid expressions, which keeps it below a 5.

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?

Content is front-loaded with the core purpose first, but the field is effectively duplicated: a Spanish block, then an English block restating the same thing, then a third copy inside inputSchema.description. The redundant bilingual mirroring roughly doubles length without adding information.

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-computation tool with a full output schema and complete annotations, the description covers purpose, exclusions, purity, determinism and execution limits — everything needed to call it correctly. Minor gap: it does not say what a malformed expression or unknown function produces, though the output schema partially covers returns.

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 all three parameters (expression, variables, decimals) are already documented — the baseline is 3. The prose adds meaning for `variables` ('named variables' usable inside expressions) but says nothing about `decimals` rounding semantics or the 0–15 range beyond what the schema states, 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 (evaluate an arithmetic expression) and enumerates the exact grammar surface: operators + − * / % ^ !, parentheses, implicit multiplication, functions like sqrt/sin/ln, constants pi/e/tau/phi and named variables. It also forecloses the closest sibling by name (bigint-calc), so an agent can discriminate 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 'Cuándo: a numeric result has to be exact or reproducible instead of estimated' plus an explicit 'No para: exact arbitrary-precision integer arithmetic (bigint-calc)'. This is the when/when-not/alternative triad spelled out rather than left to inference.

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