dual_iterate

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

With no annotations provided, the description carries the full burden, and it excels. It discloses that the tool is 'Read-only: returns the generated code to the caller; does NOT write to disk' and explains the internal loop, the fact that Claude sees only the final accepted code, and the meaning of return fields like `history` and `self_review_applied`. It also details the stopping conditions and the role of `quality_threshold`. This is comprehensive behavioral transparency.

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 long but every sentence earns its place. It is front-loaded with the core mechanism, then covers usage, alternatives, read-only behavior, and return format. Despite the length, it is densely informative and structured logically. No fluff or repetition of schema details; it adds value throughout.

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?

Given the tool's complexity (internal loop, 4 parameters, no output schema), the description is remarkably complete. It explains the full process, the return object structure (including `success`, `code`, `mode`, `iterations`, `execution_time_ms`, `metadata`, `history`, `final_review`, `self_review_applied`), the read-only nature, and how to persist results via `write_files_atomic`. It also addresses the user-facing benefit (reduced token output). Nothing critical is missing.

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 100%, so the baseline is 3. The description adds meaningful context beyond the schema: it explains the effect of `quality_threshold` with concrete ranges ('0.7 (default) = balanced. 0.85+ = strict... 0.5 = lenient') and clarifies that the loop stops at `max_iterations` regardless of threshold. It also links `include_history` to the return value. This enriches parameter understanding without redundancy, so 4 is appropriate.

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 opens with a specific verb and resource: 'Code generation with an internal review loop,' and clearly explains the iterative process. It distinguishes itself from siblings by naming alternatives: 'For multi-agent TDD with parallelism + tests, use `parallel_agents`. For one-shot generation without iteration, use `generate_file`.' This fully clarifies what the tool does and when it is unique.

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?

Explicit usage guidance is provided: 'Use for complex single-file generation where you would otherwise pay the token cost of reviewing iterations in-chat.' It also states when not to use it by pointing to alternatives: `parallel_agents` for multi-agent TDD and `generate_file` for one-shot generation. This gives clear when/when-not/alternatives, exceeding the minimum.

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