codegen

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 clearly states the two possible return statuses ('ok' with code, 'needs_clarification' with clarifications) and explains the stateful session_id behavior. This is strong transparency for a generation tool, though it omits details about error handling or side effects.

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 three sentences, immediately front-loaded with the primary purpose. Every sentence earns its place: purpose, return/status behavior, and follow-up instruction. There is no filler or repetition of schema information.

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?

Although there is no output schema, the description fully explains the return format (status values and associated fields) and clarifies the session_id lifecycle. For a tool with one required parameter and two well-documented optionals, this is complete. The mention of `clarify` as a companion tool adds necessary contextual linkage.

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 all three parameters with 100% coverage, giving a baseline of 3. The description adds meaningful semantics for `session_id` by specifying that it should be passed back on follow-up calls to preserve context, which goes beyond the schema's generic wording. It does not add further detail for `prompt` or `context`, but the schema is sufficient.

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 starts with a specific verb+resource: 'Generate Python code for the cfx stage from a natural-language prompt.' This clearly distinguishes it from siblings like run_code or validate_code, which handle execution and validation rather than generation.

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 the primary use case (generating code from a prompt) and explicitly directs the agent to use the `clarify` tool when the status is 'needs_clarification', which is a clear alternative path. It also instructs to pass `session_id` on follow-up calls, giving actionable usage context. It does not explicitly mention when not to use it or compare with siblings, so a perfect score is not warranted.

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