run_lisp

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

With no annotations, the description carries the full burden, but it only discloses the *MCPRES* return mechanism. It fails to mention that this tool can execute arbitrary code with full drawing access, potentially destructive side effects, error handling, or that changes might not be undoable. This is a significant transparency gap for a code execution 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 sentence that front-loads the core action ('Eval AutoLISP code') and adds only necessary clarifications. It is appropriately sized and easy to parse.

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?

Given the tool's power and risk (arbitrary code execution), the description is too brief. It omits warnings about side effects, destructive potential, when to prefer this over specific drawing tools, and does not explain the output schema despite it existing. A complete description would need to address these aspects.

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 single 'code' parameter is described as containing AutoLISP code, and the note about multi-line and multiple expressions adds meaning beyond the bare schema. However, it does not provide examples, size limits, or clarify expected return format beyond the *MCPRES* hint, leaving some ambiguity.

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 'Eval AutoLISP code' with a specific verb and resource, and notes support for multi-line and multiple expressions. This distinguishes it from sibling tools that perform specific CAD operations, making its purpose unambiguous.

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 implies usage for evaluating arbitrary AutoLISP code when no dedicated sibling tool exists, and provides the *MCPRES* mechanism for returning data. It does not explicitly state when not to use it or mention alternatives, but the context is fairly clear.

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