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

Annotations already declare readOnlyHint, openWorldHint=false, idempotentHint and destructiveHint=false, and the description does restate those ('no network access, no stored state'), which is redundant. However it adds genuinely new behavioral facts: determinism and concrete operational limits (64 KB JSON input, 1 s per call, 1 MB result) that an agent cannot derive from the annotations.

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?

Well front-loaded and organized with labeled segments (Cuándo / No para / Efectos secundarios / Límites), but the entire content is duplicated in Spanish and English, roughly doubling length with no new information for the reader. The structure is good; the volume is wasteful.

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 an output schema present, the description need not explain return values, and it covers everything else an agent needs: dimensionality limits, the compatibility precondition, determinism, and resource ceilings. Combined with full schema coverage and rich annotations, 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 description coverage is 100%, so the baseline is 3; the description earns above baseline by adding the cross-parameter constraint that columns of A must equal rows of B, which the schema cannot express. It does not explain the row/column array layout in more depth, but that is already covered by the schema descriptions and examples.

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 ('Multiplica dos matrices') plus the size ceiling (up to 20×20) and the dimensional compatibility rule (columns of A must equal rows of B). It explicitly excludes the closest sibling ('No para: transponer una matriz (matrix-transpose)'), so an agent can distinguish it from matrix-transpose, matrix-determinant and matrix-inverse without opening a 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?

Gives an explicit positive condition ('When: a numeric result has to be exact or reproducible instead of estimated') and an explicit negative with the named alternative ('Not for: transposing a matrix (matrix-transpose)'). Both the when and the when-not are stated, leaving nothing to inference.

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