eda_sch_primitive_attribute_modify

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

No annotations exist, so the description must carry the behavioral burden. It reveals that the tool modifies an attribute and returns an attribute object, but it does not disclose mutation implications, whether changes are reversible, when undefined is returned, whether the object is modified in place, or any permission/error considerations. For a mutation tool this is insufficient.

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 dense and front-loaded with the method name and signature, and the trailing '修改属性' / 'returns' lines are minimal. The long type signature is relevant and not padded with fluff, though it lacks human-readable structure and repeats the operation concept in the Chinese phrase.

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?

There is no output schema, so the description must explain return behavior and usage context, but it only says 'returns: 属性图元对象' and omits the possible undefined result from the Promise signature. It also lacks examples, enum definitions, preconditions, and explanation of how to format the args array in practice, leaving an agent under-equipped for a mutation call.

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?

Although the schema has 100% generic description coverage, the actual parameter details are thin: 'args' and 'windowId' only. The description compensates by providing a full signature with primitiveId types and the complete property object shape (x, y, rotation, color, fontName, fontSize, bold, italic, underLine, alignMode, fillColor, key, value, keyVisible, valueVisible) including nullability. It does not, however, explain enum values, coordinate units, or the semantics of null, so it does not earn a 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?

The description clearly states the operation via the method signature 'sch_PrimitiveAttribute.modify' and the Chinese phrase '修改属性' (modify properties), identifying a specific resource (primitive attribute) and action (modify). This distinguishes it from sibling tools like eda_sch_primitive_attribute_create, _delete, _get, and the more generic eda_sch_primitive_object_modify.

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 instead of the many sibling modify/create/get tools, nor any mention of preconditions or alternatives. The signature alone does not explain the selection scenario.

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