eda_pcb_primitive_string_create

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

With no annotations provided, the description must carry the full burden of behavioral disclosure. It only states the signature and return type (Promise<IPCB_PrimitiveString | undefined>), implying it may return undefined, but does not explain side effects, error conditions, or whether it modifies the current document. There is no mention of required permissions, layer constraints, or what happens if parameters are invalid. This is a significant gap for a mutation tool.

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 a single line of code signature followed by two short Chinese phrases. While extremely concise, it is not structured as helpful prose; it is a raw signature dump that an agent must parse. There is no front-loading of intent or explanation. It is under-specified rather than concisely informative, so it does not earn high marks for structure.

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 tool with 13 parameters, no output schema, and no annotations, the description is woefully incomplete. It fails to explain return behavior beyond the type, does not describe what the created primitive looks like, and offers no guidance on parameter constraints or prerequisites. An agent would need to consult external documentation or guess at many details. The description is inadequate for reliable invocation.

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 defines an 'args' array with a generic description, leaving all parameter semantics to the description. The description includes the full function signature with parameter names and types (layer, x, y, text, fontFamily, etc.), which provides basic meaning. However, it does not explain units (e.g., for fontSize or rotation), allowed values, or the meaning of fields like alignMode or reverse. The agent gets names and types but no detailed guidance on how to populate them correctly.

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 includes the function signature 'pcb_PrimitiveString.create(...)' and a Chinese phrase '创建文本' (create text), which clearly states the tool creates a text primitive on a PCB. However, it lacks a natural-language explanation of the tool's purpose or how it fits into the broader primitive family. It is distinguishable from siblings like delete/get/modify, but the description is just a signature dump, not a proper explanation.

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 gives no guidance on when to use this tool versus alternatives. It does not mention prerequisites (e.g., an active PCB document), nor does it exclude cases like schematic text (which would use eda_sch_primitive_text_create). The agent receives no contextual help in selecting this tool over its many siblings.

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