run_agent

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

The description discloses the asynchronous behavior (returns session_id immediately instead of waiting for completion) and explicitly instructs to poll until 'complete' or 'failed'. This is critical context since no annotations exist. It does not cover side effects like cost or auth, but the core execution model is well explained.

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?

The description is exactly two sentences with the primary action and return value in the first and the polling instruction in the second. There is no filler, and it is front-loaded with the key information, making it highly concise and well-structured.

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 that there is no output schema, the description appropriately explains the return value (session_id) and the necessary follow-up polling workflow. It complements the schema by covering the overall lifecycle. It could mention error handling beyond 'failed', but the current guidance is sufficient for the tool's moderate complexity.

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?

The schema already provides 100% coverage with descriptions for all three parameters (agentId, settings, instructions), so the baseline is 3. The tool description adds no extra parameter semantics beyond mentioning agentId in the narrative, which does not enhance the schema's own description.

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 clearly states the action (runs a saved agent), the resource (a preconfigured NeuralVerge agent identified by agentId), and the immediate result (returns a session_id). It also distinguishes this tool from siblings like run_research or run_search by focusing on running a reusable, preconfigured workflow rather than a specific task.

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 provides clear context: you use this tool when you have a saved agentId and want to execute it. It also instructs to poll get_session_status afterward, which is a useful follow-up guidance. However, it does not explicitly mention alternatives or when not to use it, so it falls short of a full 5.

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