start_agent_run

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

With no annotations, the description fully carries the burden and succeeds: it discloses the immediate failure on insufficient IQ credit, the 2-minute inline poll, the typical 3–5 minute run duration, and the report format (markdown, signals, evidence links, confidence rating). These are non-obvious behavioral traits that the schema would never reveal.

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 sentences with zero filler: the first states the purpose and output; the second covers the credit-failure condition; the third explains polling, the fallback to get_agent_run, and expected duration. Every sentence earns its place, and the most important information is front-loaded.

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's complexity (8 params, nested object, async execution) and the absence of an output schema and annotations, the description is remarkably complete. It covers the input type, the processing pipeline, the output structure, the failure mode, the timeout behavior, and the follow-up mechanism—enough for an agent to select, invoke, and correctly interpret the result.

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 100%, so the baseline is 3. The description only adds that the question is plain-English and mentions searching across platforms, but it does not add meaning beyond what the schema already provides for parameters like mode, max_post, platforms, or available_credits. It neither improves nor harms parameter understanding.

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 opens with 'Start a Rolli Agent investigation' and proceeds to detail the full workflow—plans search strategy, queries Rolli IQ, analyzes posts, produces a markdown report with signals and confidence rating. This clearly distinguishes it from sibling search tools like keyword_search and user_search, and from get_agent_run, by framing the agent's autonomous investigation lifecycle.

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 gives clear context on when to use the tool (for plain-English investigations) and explains polling behavior: it polls up to 2 minutes, and if not finished, returns a run ID and directs the caller to get_agent_run. This is useful guidance, but it does not explicitly contrast with simpler search tools or state when not to use the agent, so it is clear but lacks explicit exclusions.

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