spawn

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

With annotations declaring readOnlyHint=false, destructiveHint=false, and idempotentHint=false, the safety profile is partly covered. The description adds valuable clarification that `role` and `write_origin` do not grant elevated permissions and that privileged work uses private launchers. It does not disclose resource cost, what a spawned session inherits, or the return format beyond what the output schema carries.

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 purpose is front-loaded and the prose is tight, but several sentences are spent on internal implementation archaeology (`_spawn_impl`, retry lineage leaking) rather than on guidance the calling agent can act on. That is informative prose but not efficiently targeted at invocation.

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?

An output schema exists, so return values need not be described. But for a 13-parameter mutation tool with 0% schema coverage, leaving eleven parameters unexplained means an agent cannot invoke it correctly without inspecting the schema's types and defaults alone.

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% across 13 parameters, so the description carries the burden. It explains only two parameters (`role` as a cognitive stance, `write_origin` as provenance labeling), leaving cwd, slim, model, effort, visible, append_system, capture_output, permission_mode, base_allowed_tools, and extra_allowed_tools entirely undocumented.

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 opening sentence gives a clear verb+resource: 'Launch a new child session in parallel.' It also draws a boundary against the private `_spawn_impl` launcher, which helps distinguish it. However, the concept of a 'child session' is jargon that isn't unpacked, and it doesn't distinguish the tool from broader siblings like open_thread.

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 states this is 'the public MCP surface' and that privileged Evolve children and watchdog retries use other paths, which gives partial routing guidance. But it never says the affirmative case – when an agent should call spawn versus alternatives in the sibling list – leaving usage largely implied.

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