geometry.matrix_inverse

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

Goes well past the readOnly/idempotent annotations: reports float64 precision (~15 digits), warns that output strings may use exponential notation like '1e-05', states that singular matrices raise an error, and sets an input size limit (n ≤ 200). These are exactly the operational facts an agent cannot get from structured fields.

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?

Four short sentences, zero filler: purpose first, then input contract, then output caveats, then the routing alternative. Every sentence adds information an agent needs at call time.

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?

Covers input shape, size cap, precision, output encoding and failure mode, which is everything needed to call it correctly. An output schema exists, so the return-value discussion is a bonus rather than a requirement, and 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 coverage is 0% and the lone parameter 'M' is a bare string array in the schema, so the description carries the full burden — and does: n×n 2D list of Decimal strings, n ≤ 200, with the return type (float64 repr strings) also characterized.

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 ('정방행렬의 역행렬을 계산한다') plus the exact implementation (numpy.linalg.inv, float64). It then contrasts itself with the sibling matrix_solve, so an agent can separate the two 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?

Explicitly routes the agent away from this tool when the real goal is solving a linear system: '연립방정식 해가 목적이면 ... matrix_solve 를 쓴다'. That is a concrete when-not condition with a named alternative, though it gives no guidance against the other matrix siblings (determinant, multiply).

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