integer_program

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

With no annotations, the description carries the full burden. It usefully discloses default bounds (0 <= x <= inf), the all-integer default for integrality, and that fun is the minimum objective, but says nothing about infeasibility behavior, return shape beyond fun, or solver/method characteristics.

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?

Front-loaded with the core operation and kept to three tight sentences with no padding; the integrality and negation notes earn their place. Slightly under-specified rather than verbose, so conciseness is not the weak point.

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 an 8-parameter, 0%-coverage, no-output-schema tool, the description is incomplete: the constraint matrix/vector parameters that define the actual problem are never explained, so an agent cannot confidently formulate a call from the description alone.

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 0% across 8 parameters, so the description must compensate. It explains c (objective), integrality, and bounds, but the five constraint/method parameters (a_eq, a_ub, b_eq, b_ub, method) are left entirely undocumented in both schema and description, which is a real gap for a MILP tool.

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+resource (minimize c @ x via scipy milp) and names the problem class (mixed-integer linear programming), which implicitly separates it from the sibling linear_program. It never explicitly routes the agent to linear_program for all-continuous problems, so sibling differentiation is only implicit.

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?

There is no explicit when-to-use guidance versus linear_program or optimize_minimize, only the implication carried by 'mixed-integer'. It does offer a useful usage note ('negate c to maximize') and integrality semantics, but nothing on exclusions or which sibling to pick.

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