extract_function

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals key traits: exact AST extraction for Python, best-effort for others, execution in a sandbox, and the return of the extracted program with per-input runs. This gives meaningful insight into how the tool behaves, though it does not mention error cases or side effects. Overall, it is transparent for the tool's complexity.

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 compact, with the primary action in the first sentence and a crucial caveat in the second. Every sentence adds value, there is no filler, and the structure is front-loaded with the core purpose. It is an excellent example of conciseness.

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 five parameters, three required, and an output schema, the description covers the main purpose, language-specific behavior, the sandbox execution, and the return type. The presence of an output schema means return details need not be fully described. The main gap is insufficient detail on `test_inputs` and potential error conditions, but overall, the description is complete enough for an agent to select and invoke the tool correctly in most situations.

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?

Schema description coverage is 0%, so the description must compensate. It explicitly explains the `call` parameter ('pass `call` to execute non-python') and implies the role of `function_name` and `language`. However, it does not describe `test_inputs` format (array of strings) or how `code` is used beyond context. The description adds some semantic value but not enough to fully cover all five parameters, especially given the lack of schema descriptions.

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 the tool's function: 'Extract a named function (with its imports + referenced helpers) into a standalone program and run it in the sandbox.' This uses a specific verb (extract) and resource (named function) and distinguishes it from sibling tools like execute_code or translate_code. It also mentions the return value, making the 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 provides conditional usage guidance: 'python3 gets exact ast extraction; other languages best-effort block extraction (pass `call` to execute non-python).' This tells the agent when to use the `call` parameter and highlights language-specific behavior. However, it does not explicitly contrast with alternatives like execute_code or state when not to use this tool, so it falls short of full explicit guidance.

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