eda_sys_math_contains_point

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

Annotations are none provided, so the description carries the full burden. It states the function signature and return type (boolean) but lacks details on edge cases such as points on the polygon boundary, coordinate system, or error handling. The line 'returns: 是否在多边形内部' clarifies the return meaning. However, it does not disclose any side effects (unlikely for a math function) or performance characteristics. For a pure geometry check, this is adequate but minimal.

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?

The description is concise, with the signature on the first line, a one-line Chinese explanation, and a return explanation. It is front-loaded with the most important information. There is no fluff. However, it repeats the function name in the signature, which is somewhat redundant, and the Chinese text is not translated, potentially inaccessible to non-Chinese agents, but that's a language issue not a structure issue.

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 simple geometry predicate, the description covers the essential purpose and parameters. But given that there is no output schema, it should clarify the return value semantics (e.g., true if inside, false otherwise) which it does. However, it lacks context on the input structures: what is a polygon represented as? What are the coordinate units? Without this, an agent might struggle to construct valid arguments. Given the complexity of polygon inputs, this is a notable gap.

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% but the schema only shows an 'args' array with generic 'items' and no per-parameter descriptions. The description includes the signature with parameter names and types (TSYS_MathPolygonInput, ISYS_MathPoint), which provides more meaning than the schema alone. However, it does not explain the structure of these input objects (e.g., coordinate format, units), which could be critical. Since coverage is high but the schema is thin, the description adds some value but not enough for complex inputs.

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 states '判断点是否在多边形内部' (determine if point is inside polygon) with a clear signature showing the polygon and point parameters. It distinguishes from siblings like eda_sys_math_contains (which likely checks containment of shapes) by specifying point-in-polygon. The name itself is also explicit. However, it doesn't explicitly differentiate from the sibling eda_sys_math_contains, which may cause some ambiguity for agents not familiar with the domain.

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 guidance on when to use this tool versus alternatives. The sibling set includes eda_sys_math_contains, eda_sys_math_intersection, and eda_sys_math_intersects, which could overlap in some contexts. The description does not explain when point-in-polygon is the right operation or mention any prerequisites (e.g., polygon format, coordinate system).

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