agents_spawn

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

With no annotations, the description carries the full burden. It discloses asynchronous behavior, immediate task-id return, a read-only default, and the worktree constraint for parallel writes. However, it omits potential side effects (e.g., resource consumption), persistence details, error behavior, and how to manage the spawned agent beyond the implied sibling tools. These gaps keep it from being more transparent.

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?

Two short, front-loaded sentences. The first states the primary action and immediate result; the second adds critical usage constraints. No wasted words, and the structure is easy to scan.

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?

At 7 parameters with 14% schema coverage, no output schema, and no annotations, the description is too sparse. It covers the core async behavior and key constraints, but does not explain required parameters like provider and work_dir, how to monitor the resulting task, or what errors/timeouts might occur. For a tool that spawns a local CLI agent, this is insufficiently complete.

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 only 14% (only isolated_worktree has a description). The description adds meaning for 'permission' via 'Use read-only unless edits are required' and for 'isolated_worktree' via 'independent Git worktrees', but it does not explain the purpose or valid values for provider, model, prompt, work_dir, or timeout_seconds. Given the low schema coverage, the description should have compensated more for these undocumented parameters.

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 function: 'Start a local CLI agent asynchronously and return a task id immediately.' This uses a specific verb and resource, and distinguishes agents_spawn from sibling tools like agents_list, agents_status, and agents_cancel, which manage or query existing agents.

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 provides actionable guidance: 'Use read-only unless edits are required' clarifies the permission parameter's default and when to change it. 'Parallel write tasks must use independent Git worktrees' sets a clear precondition for concurrent writes. It stops short of explicitly naming alternatives or when to choose this tool over siblings, but the context is clear.

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