execute

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

No annotations present, but description discloses behaviors: error hints, show() output, need to call measure() after booleans, and named_face helper.

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?

Description is informative with multiple sentences but each adds value; front-loads main purpose.

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?

Covers key behaviors and helpers, though could mention state persistence and output schema. Output schema exists, so return values are covered else.

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?

Only parameter 'code' has 0% schema coverage, and description gives examples of what code may contain but does not specify format or constraints.

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?

Clearly states 'Execute build123d Python code in the persistent session', specifying the verb and resource. Differentiates from siblings like 'measure', 'export', etc.

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 guidance on handling errors with fix hints and use of specific functions (show, measure, named_face). Does not exclude alternatives implicitly.

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