run_thronglet

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

With no annotations, the description carries the burden and does so well: it documents both return shapes ({session_id, text, stop_reason, usage, duration_s, warnings?} and the structured variant), the background contract ({session_id, state, queued}), and the 21600s default timeout. It omits side-effect/risk disclosure (the agent executes commands in the user's tree) and failure/timeout behavior, which keeps it from a 5.

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?

Front-loaded with the core action and return contract, then progressive detail on structured output and background mode. Dense and semicolon-heavy, but nearly every clause carries operational information; the listing-name note is the only mildly incidental line.

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?

For a 7-parameter tool with no output schema and no annotations, the description covers return values for both sync and background modes plus the default timeout, which is what an agent needs to call it. Gaps remain around error/timeout handling and the privilege implications of running an agent in a working tree.

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 coverage is 100%, so baseline is 3, but the description adds meaning the schema alone does not: that schema swaps `structured` in place of `text`, that background changes the returned shape and requires wait_thronglet, and that description surfaces the run in session listings. Only `cwd` and `timeout_s` get no added context beyond the schema.

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?

States a specific verb ('Runs') plus resource ('an agent of an installed harness') and scope ('on a task in cwd'), then distinguishes itself by pointing at list_harnesses for valid agents and wait_thronglet for async collection. An agent can separate this from send_message/cancel_thronglet without opening a schema.

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?

Gives clear routing for two cases: fetching valid agents via list_harnesses and retrieving async results via wait_thronglet when background: true. It does not, however, contrast itself with send_message (continuing an existing session) or state when not to launch a new run, so it stops short of full when/when-not coverage.

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