eda_sch_primitive_component_delete

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

No annotations are provided, so the description carries the full behavioral disclosure burden. It does disclose the return type (Promise<boolean>) and its meaning ('删除操作是否成功' - whether deletion succeeded), which is useful. However, it omits critical behavioral details for a destructive mutation: what happens when deleting multiple IDs where some fail (partial failure semantics), whether deletion cascades to connected pins/wires, and whether the operation is reversible. For a delete tool with zero annotation coverage, this is a significant gap.

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 terse and front-loads the signature, which is an efficient structure. The Chinese explanation and return-value note add minimal but relevant information. However, the bilingual mixing (English signature, Chinese descriptions) could cause ambiguity for non-Chinese agents, and the brevity sacrifices informative content for compactness.

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?

This is a destructive operation with no annotations and no output schema, yet the description provides only a bare signature and a one-line return note. It omits the structure of the args array, the meaning of the primitiveIds parameter in practical terms, how windowId is used (only in schema), and failure/edge-case behavior. For a 2-parameter mutation tool without annotation or output-schema support, an agent cannot confidently construct a correct 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?

The schema reports 100% coverage, but the args parameter's items are empty {} objects, so the actual content is opaque. The description's signature partially compensates by declaring the parameter type (string | ISCH_PrimitiveComponent | Array<string> | Array<ISCH_PrimitiveComponent>), which tells the agent what kinds of values are accepted. However, it doesn't explain what ISCH_PrimitiveComponent is, how IDs are formatted, or how the args array maps to the signature parameters. The windowId parameter is only documented in the schema, not the description.

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 verb (delete) and resource (PrimitiveComponent) via the signature and the Chinese '删除器件' (delete component). It's evident this deletes schematic primitive components. However, it doesn't distinguish itself from the many sibling _delete tools (arc_delete, circle_delete, etc.) beyond the component-specific name, and the description essentially restates what the name already conveys.

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?

No guidance is given on when to use this tool versus alternatives. Among the dozens of sibling primitive delete tools (eda_sch_primitive_arc_delete, eda_sch_primitive_bus_delete, eda_sch_primitive_pin_delete, etc.), nothing in the description tells the agent when component deletion is the right choice or what distinguishes it. The tool operates on schematic primitives of type component, but this is never stated as a selection rule.

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