spawn_subagent

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

With no annotations, the description carries full burden. It discloses key behaviors: the agent runs once, has no memory between calls, is destructive when `write_files:true` (saving code to work_directory which auto-creates), and by default returns code inline. It also describes the return structure including success, verdict, files_analyzed, files_written, etc. No contradictions.

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 front-loaded with the main purpose, then provides usage guidelines, behavioral warnings, and return details. Every sentence is informative, but it is somewhat lengthy. However, for a complex tool with many behavioral nuances, the length is justified and there is no redundant 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?

Given the tool has 7 parameters, no output schema, and is moderately complex, the description covers all necessary aspects: purpose, when to use, parameter usage, behavioral side effects, and detailed return structure. It even lists the fields returned (success, role, task, backend_used, response, verdict, files_analyzed, files_written, work_directory, suggested_tools, processing_time_ms, metrics), compensating for the lack of an output schema.

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 baseline is 3. The description adds extra value beyond schema: explains the difference between verdict modes, clarifies that work_directory defaults to a timestamped path, and emphasizes that task should include file paths and acceptance criteria. It also provides context on how role enums map to TDD phases, which the schema already details but the description reinforces.

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 purpose: 'Spawn one AI agent with a predefined role + system prompt and run it to completion on a single task.' It distinguishes from sibling tools by explicitly naming alternatives: 'For multi-agent TDD parallelism with quality gates, use parallel_agents. For multi-backend consensus on a question, use council.' This makes the purpose unmistakable.

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 explicitly says when to use this tool: 'Use when the work fits a clear role...' with examples. It also provides guidance on what to include in the task: 'Pass file paths and acceptance criteria in `task` — the agent has no other context.' It warns about destructive behavior and defaults, and directs to alternatives for parallel or consensus work.

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