subagent_spawn

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

No annotations present, so description carries full burden. It discloses that only files under cwd are accessible, external paths must be declared and pass security checks, and that long timeouts need explicit authorization. This adds behavioral context beyond the basic 'start a run'.

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?

Description is a single paragraph of three sentences with no wasted words. It front-loads the purpose and then adds important behavioral details. Could benefit from slight structuring (e.g., bullet points for parameters) but overall efficient.

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?

The description covers key aspects like agent type, timeout, and external paths, but leaves many parameters (items, fork_context, dry_run, max_steps) undefined. With 11 parameters and no annotations, the description is incomplete for full autonomous selection. Output schema exists but doesn't compensate for missing parameter semantics.

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%, yet the description only clarifies agent_type, timeout_seconds, allowed_external_roots, and explicit_authorizations. Parameters like items, fork_context, dry_run, max_steps are left unexplained. Given the high parameter count, more parameter-level detail is needed.

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 starts an Open Subagent MCP run. It distinguishes between 'explorer' (read-only) and 'worker' (writable) agent types, which differentiates it from sibling tools like subagent_close or subagent_rollback.

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?

Provides clear context: agent type selection based on need, default timeout guidelines (<=120 for normal tasks, >120 requires explicit authorizations), and note about file access. Does not explicitly list when-not-to-use, but the guidance is strong and implies appropriate use.

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