parallel_agents

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

With no annotations provided, the description carries the full burden and does well: it warns about destructive behavior when write_files is true, explains that files are written to work_directory subdirectories (red/green/refactor), and describes the iteration loop termination condition. It also includes the full return structure, adding useful context beyond annotations.

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 each sentence earns its place: it covers the workflow, use cases, alternatives, destructive warning, and return structure. It is well-organized and front-loaded with the core purpose, making it dense yet scannable. Not overly verbose for the complexity involved.

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 (6 parameters, no output schema, no annotations), the description is remarkably complete. It explains the process in enough detail to predict behavior, provides safety warnings, states alternatives, and lists the exact return fields. The only minor gap is not elaborating on cleanup or permissions, but the return structure and schema coverage fill most needs.

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 covers 100% of parameters with descriptions, providing a solid baseline of 3. The tool description enriches this by explaining the behavioral impact of write_files (destructive, writes to subdirectories) and mentions max_iterations as the loop limit. This extra context adds value beyond the 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 the tool runs a test-first development workflow as a graph of parallel agents, detailing the decomposer, RED/GREEN phases, and quality reviewer. It distinguishes itself from siblings by explicitly naming spawn_subagent and dual_iterate as alternatives, making its unique role obvious.

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?

It provides explicit when-to-use guidance: 'Use for self-contained features that benefit from test-first discipline and can be parallelized.' It also gives concrete alternatives: 'For a single agent on a single task, use spawn_subagent' and 'For a generate→review→fix loop on one code blob (no test infrastructure), use dual_iterate.' This is exemplary usage direction.

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