Research Run

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

Annotations already declare non-readOnly, non-idempotent, open-world behavior, so the bar is lower; the description still adds real value by disclosing that execution is asynchronous and that retries or resubmissions spawn new paid jobs. That cost/idempotency consequence is exactly the kind of context annotations cannot express. It stops short of describing latency, engine failure behavior, or what happens when a paid job errors.

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?

Short and front-loaded: the core action and its async nature come first, then the cost caveat, then the follow-up pointer. Three tight sentences with no filler, though the phrasing 'a retried or resubmitted Task is a new job' is slightly redundant with the preceding clause.

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 no output schema, the description correctly discloses that a run_id is returned and names the tool to consume it, which is the critical missing piece for a fire-and-forget job. Combined with the cost and async disclosures, an agent has enough to invoke it correctly; only error/failure semantics are absent.

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 both parameters (query, engine) are already fully documented with defaults and enum-like values in the schema. The description adds only the phrase 'selected engine' and confirms the query goes to a paid job — marginal value over the schema. Baseline 3 applies.

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 and resource ('Run one research job on the selected engine') and adds the key trait that it executes as a background Task. It does not explicitly differentiate itself from fixed-engine siblings like research_deep or research_web, so the agent must infer that 'selected engine' is the differentiator.

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 a clear follow-up path ('Use get_research_run with the returned run_id to inspect or recover the result') and warns that each submission is a separately paid job, which implicitly discourages blind retries. However, it never states when to prefer research_deep/research_web/research_compare or when this generic engine-selecting entry point is the right choice.

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