start_run

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

Beyond the annotations (readOnly=false, idempotentHint=true), the description discloses model cost, approval persistence in the Open Science UI, and the narrow idempotency guarantee tied to daemon lifetime and a 24-hour window. This materially changes how an agent should reason about retries and side effects, and it does not contradict the annotations.

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 dense sentences carry high-value information: cost, session continuity, cwd constraint, approval behavior, return value, and idempotency limits. There is no filler or repetition of schema content.

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?

Given the tool has six parameters, no output schema, and meaningful side effects, the description covers the critical operational facts: cost, approvals, run ID return, cwd constraint, and retry protection limits. It is slightly weak on how to discover or supply session_id and what turn_intent='plan-first' implies, but it is largely sufficient 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 only 17%, so the description must compensate. It adds meaning for cwd (must match the session directory), session_id (continue an existing session), and idempotency_key (retry limitations), but it does not clarify project_id, prompt, or turn_intent, leaving some parameter semantics to inference.

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 names two distinct actions: submitting research and continuing an existing session, with a clear resource (a run). It implicitly distinguishes itself from read-only siblings like get_run, wait_run, and list_sessions by focusing on submission/continuation, so an agent can tell when to select it.

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 gives concrete usage context: start a new submission or continue a session, and requires cwd to match the session directory on follow-ups. It also directs the agent to poll/wait on the returned run ID, suggesting the appropriate follow-up tools, though it does not explicitly name alternatives or exclusions.

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