spawn

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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, so the mutation/safety profile is covered. The description adds real behavioral context: `role` and `write_origin` do not confer elevated permissions, privileged children go through private launchers, and retry lineage is deliberately kept out of this contract. It does not say whether the call blocks or returns immediately, which is a notable gap for a launch tool.

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?

Three tight sentences, front-loaded with the action, and each adds a distinct point about surface routing or provenance. The middle clauses are jargon-heavy ('server-owned launchers', 'retry lineage/config'), but no sentence is filler.

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, and annotations cover the safety profile. But for a 12-parameter mutation/launch tool with zero schema descriptions, the definition omits entirely how the documented-but-unexplained parameters affect behavior (e.g. permission_mode, capture_output, visible). It is adequate on architecture and inadequate for correct invocation.

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 12 parameters, so the description carries the full documentation burden. It only explains two of them (`role`, `write_origin`) and says nothing about prompt, model, effort, cwd, slim, visible, capture_output, permission_mode, extra_allowed_tools, or append_system. With under 20% of parameters addressed, it does not compensate for the schema gap.

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 states a concrete verb and resource ('Launch a new child session in parallel'), which is immediately actionable. It also distinguishes the public MCP surface from the private server-owned launchers and the `_spawn_impl` retry path, so an agent can tell this apart from related entry points. It is slightly weaker on differentiating from session/sibling tooling like `peers` or `ask`.

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 clarifies which surface to use (public vs private launchers, `_spawn_impl` for watchdog retries), which is useful routing. However, it never states when an agent should spawn a child session at all versus using `ask`, `broadcast`, or `peers`, nor any prerequisite or budget constraint despite a `spawn_budget_status` sibling. Usage is implied rather than instructed.

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