execute

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

With no annotations, the description must carry the burden of disclosure. It reveals the entry point requirement and the stdout-to-response mechanism, which are important behavioral traits. However, it omits critical details such as side effects, security considerations, available libraries, or execution environment, leaving the agent with an incomplete picture of the tool's behavior.

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 exceptionally concise, consisting of two sentences that deliver the core contract: execution model, entry point, and output handling. Every word serves a purpose, and the most critical information is front-loaded with the 'Raw Python passthrough' label.

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?

Despite the tool's potentially high complexity (arbitrary Python execution), the description covers the essential execution contract. However, it lacks information about interaction with the CAD environment, error handling, timeouts, or available APIs, which are likely relevant given the sibling tools. The absence of an output schema makes this gap more noticeable, as agents cannot rely on structured output descriptions.

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 only defines 'script' as a string with 0% coverage, so the description must compensate. It does so by explaining that the script must define a `run(_ctx)` function and that print output is captured as the response. This adds meaningful context about the expected content and structure of the script parameter, going beyond the bare schema.

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 it is a raw Python passthrough, which is a specific and distinct purpose compared to the many CAD-specific sibling tools. It explicitly identifies the verb (execute) and the resource (Python script), leaving no ambiguity about its function.

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 does not provide any guidance on when to use this tool versus alternatives. It neither suggests appropriate scenarios nor warns against misuse. The name 'execute' implies it is for advanced scripting, but that is not stated explicitly, leaving the agent without clear decision criteria.

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