Execute AutoLISP

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

The description is transparent about the denylist, quotes-as-data behavior, and warns it is 'NOT a security boundary' with write channels beyond the denylist. However, the annotation readOnlyHint:true directly contradicts this, since executing arbitrary AutoLISP can mutate drawing state. This is a serious annotation contradiction, so the score is 1.

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 front-loaded with the primary purpose, immediately gives an example, and uses every remaining sentence to convey necessary safety context. It is appropriately sized for a potentially dangerous escape-hatch tool with no filler.

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 an arbitrary LISP execution tool, the description covers backend, usage example, guardrail limitations, and recommends safer alternatives; the output schema handles return formatting. The main gap is the contradiction with readOnlyHint and the lack of explicit error/rollback behavior, but overall it is reasonably complete for its complexity.

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 already documents the single 'expression' parameter with 100% coverage, giving a baseline of 3. The description adds meaningful extra semantics by explaining that text inside double quotes is treated as data and by providing a concrete example, which clarifies how to construct the expression string.

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?

States a specific verb ('Execute') and resource ('AutoLISP expression') and adds the constraint 'COM backend only'. The example makes the intended use clear. However, it does not explicitly distinguish itself from similar siblings like lisp_execute_code or lisp_load_macro, so differentiation is left implicit.

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?

Provides clear guidance to 'Prefer the typed tools', steering agents toward safer alternatives and implying this is a fallback. The COM backend restriction is a concrete usage constraint. It does not name specific typed tools or state exactly when raw LISP is the only option, leaving some room for inference.

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