run

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

With no annotations, the description carries the safety/behavior burden, and it does disclose a non-obvious trait: sessions return only when reachable, while tasks return a non-messageable run handle. However, it does not mention side effects, auth requirements beyond the schema's sandbox/permissions notes, or how the returned handle is consumed.

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 sentences with no filler; the core action is front-loaded and the return-behavior nuance is compressed into the second sentence. Every sentence earns its place.

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?

With eight parameters, five enums, no output schema, and no annotations, two sentences leave too many operational gaps (defaults, host/runtime choice, handle consumption). The session/task distinction helps, but an agent still lacks enough to call this complex tool confidently.

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 25%, and the description compensates only for `kind` by defining session vs task return behavior. cwd, args, host, runtime, and prompt remain semantically unexplained in either the schema or the description.

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 uses a specific verb ('Launch') with a clear resource ('an instructed agent') and immediately defines a meaningful sub-distinction between sessions and tasks. This makes it easy to distinguish from the sibling management commands list, stop, and output.

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 implies the tool is for starting an agent and clarifies the session/task return contract, but it never states when run should be preferred over list/stop/output or gives exclusions/prerequisites. Usage context is inferable from the name and siblings, not explicit.

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