gcd_lcm

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

No annotations are provided, so the description carries the full behavioral burden, and it discloses almost nothing beyond domain validity: behavior with a single-element array, zeros, or negative numbers is unstated, as is determinism or purity. The only behavioral disclosure is the minimum-arity requirement, which is a minor piece of context.

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?

Two short sentences, front-loaded with the return values, followed by the input format and a compact inline example. Every sentence earns its place with zero filler.

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 narrow, pure math function with an output schema present, the description covers the essentials: what is computed and what input shape is acceptable, so return-value details need not be repeated. The remaining gap is domain-edge behavior (zero/negative/single input), which is minor for this tool class.

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?

With 0% schema description coverage, the description must compensate, and it does: it clarifies the parameter is a list of integers and adds the cardinality rule ('two or more') that the schema does not enforce, plus a concrete example '[12, 18, 24]'. It stops short of edge-case semantics (empty array, single value, negatives), so not a full 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 the specific verb ('Return') and the exact resources computed ('greatest common divisor and least common multiple'), and it also names the second return value. No sibling tool (is_prime, prime_factorization, evaluate, etc.) overlaps with this operation, so the purpose is unambiguous from the name-plus-description alone.

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?

Usage is implied by the operation itself, and the description adds the one real usage constraint ('two or more integers'), which tells the agent this is not a single-argument call. However, it never states when to prefer this over a general evaluator or prime_factorization, and there are no exclusions or prerequisites.

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