eda_sch_primitive_attribute_get_all

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 key behavior of the optional parameter (retrieves all page attributes when parentPrimitiveId is omitted), which is valuable. However, it doesn't explicitly state this is a read-only, non-destructive operation (though inferred from the getter name), nor does it mention any potential performance implications, pagination, or ordering. For a simple get-all, this is acceptable but not comprehensive.

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 brief—just a method signature, a one-line purpose, a remark, and a return type note. It is front-loaded with the purpose and provides essential detail in the remark. No fluff or repetition. The Chinese/English mix is understandable, and the structure is clean. A minor improvement would be to separate the purpose from the signature more clearly.

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 get-all tool, the description covers the critical scoping behavior (parent vs. page-level) and the return type. However, it does not specify the structure of ISCH_PrimitiveAttribute beyond the name, nor does it mention ordering, filtering, or potential error conditions. The lack of an output schema means the agent must infer the attribute object's fields from context. Considering the domain complexity, a bit more detail on the returned objects would improve completeness, but the core usage is clear.

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?

The input schema only describes generic wrapper parameters (args array and windowId), not the actual domain parameter parentPrimitiveId. The description compensates by showing the method signature with its optional parameter and explaining the effect of omitting it. This adds significant meaning beyond the schema, which is otherwise opaque. Without the description, an agent would not know how to specify the parentPrimitiveId.

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 '获取所有属性' (get all attributes) and provides the method signature with the exact return type. The tool name is also self-explanatory. It distinguishes from the singular 'get' sibling (eda_sch_primitive_attribute_get) by the 'get_all' phrasing, though it doesn't explicitly contrast with the ID-only variant 'get_all_primitive_id'. Clear enough for an agent to know it retrieves full attribute objects.

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?

The description contains a remark about the optional parentPrimitiveId behavior (not passing it yields all attributes in the page), but no explicit guidance on when to choose this tool over alternatives like eda_sch_primitive_attribute_get or eda_sch_primitive_attribute_get_all_primitive_id. The agent is left to infer the appropriate context from the name and signature. No exclusions or alternative recommendations are given.

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