start_run

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

With no annotations, the description carries the burden and does well: it discloses the async/long-running nature ('runs take several minutes') and what is returned ('the run id'), which is exactly the behavior an agent needs before calling. It does not say whether runs are costly, cancellable (stop_run exists), or whether max_rounds changes cost/latency, leaving some behavioral gaps.

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 purpose, then compact per-parameter glosses, then the follow-up workflow in one clause. Every sentence carries information; nothing is padded.

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 an async job-starting tool with an output schema, the description covers the essentials: what it does, the meaningful inputs, and the polling path. The unexplained max_rounds parameter is the main remaining hole.

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%, so the description must compensate. It gives useful semantics for three of five params ('given': facts kept exactly as written; 'standards': what a good answer must do; 'pitfalls': mistakes to avoid), but 'problem' and 'max_rounds' — the latter being a knob with real cost implications — are never mentioned.

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 ('Start a ThinkerWave run') plus scope ('hard, open-ended problem'), which distinguishes it from sibling tools that are all about inspecting or stopping existing runs. An agent can route the request without opening the 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?

Explicitly frames the intended input class ('hard, open-ended problem') and prescribes the downstream workflow: 'check back with run_status, then get_answer', naming both siblings in order. It lacks an explicit when-not (e.g. don't use for quick/simple questions), which keeps it below a 5.

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