run_paragraph_async

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

Adds real behavioral context beyond annotations: execution is non-blocking and requires a poll-with-get_paragraph_status workflow, and chart/visualization settings are preserved automatically — a useful side-effect disclosure for a non-idempotent execute tool. It does not cover permissions or concurrency limits, which is the remaining gap.

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 the core behavior and the immediate follow-up workflow in the first two sentences; the Args block is compact and, given 0% schema coverage, each line earns its place.

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 an output schema exists, return values needn't be described, and the description supplies the async lifecycle (start → poll status → read results) an agent needs to use it correctly. Minor omissions are auth requirements and what a failed run looks like, but the definition is usable as-is.

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 carries the full burden and largely does: it explains notebook_id and paragraph_id as identifiers and clarifies that params is an optional dict of dynamic form values with a concrete example ({"city": "Seoul"}). That example goes meaningfully beyond the bare anyOf object in the schema, though the format of the IDs themselves is unstated.

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 paragraph execution') plus the defining behavioral distinction ('return immediately without waiting for results'), which is exactly what separates it from the synchronous run_paragraph and batch_run_paragraph siblings. An agent can pick this over its look-alikes without opening either 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?

Gives an explicit usage scenario ('run multiple paragraphs in parallel') and names the correct follow-up tools (get_paragraph_status, get_paragraph) as the alternatives for polling and retrieving output. It stops short of stating when NOT to use it (e.g. use run_paragraph for a single blocking call), leaving that inference to the agent.

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