geometry_operation

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

No annotations are provided, so the description carries the full burden. It discloses the set of operations but does not mention whether the tool modifies any workspace state (the session parameter exists), dimension requirements, point ordering for polygon area, or error behavior. While the tool appears computational and likely pure, these gaps mean behavioral transparency is only partially addressed.

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 sentences: the first is front-loaded with a clear capability list, the second provides a practical usage hint. No filler or redundancy; every word earns its place.

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?

The output schema and high schema coverage handle return values and parameter formats, so that aspect is covered. However, the description omits critical constraints (e.g., all points must have the same dimension, polygon vertices likely need ordering, polytope_volume needs at least n+1 points in n dimensions). Without annotations, these omissions leave an AI agent uncertain about valid inputs and potential failures.

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%: operation lists allowed values, points describes coordinate lists, and session explains workspace behavior. The description's operation list merely repeats what the schema already states, adding no new semantic detail. Baseline 3 is correct because the schema handles parameter semantics adequately.

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?

The description clearly states a specific verb phrase ('Computational geometry on point sets') and enumerates exact operations: euclidean distance, polygon area, polytope volume, convex hull vertices, and convexity tests. This distinguishes it from sibling tools like evaluate_sage and other mathematical operations, leaving no ambiguity about scope.

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 states 'Prefer this over evaluate_sage for these,' providing a clear alternative and indicating when this tool should be chosen. This is direct, actionable guidance that differentiates from a general-purpose evaluator, which is the most relevant sibling.

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