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

Beyond the annotations (non-read-only, open-world, non-idempotent), the description adds substantive behavior: it returns a batch_run_id for tracking, plan gating and input-set caps apply, and every node executes once per input set regardless of lock state. The quota/plan caveat is exactly the kind of context annotations cannot express. It does not say what happens on partial failure or whether re-running is safe, which would have completed the picture.

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?

Four dense sentences, each carrying distinct information, with the core action front-loaded. The closing clause about result locks is terse and slightly cryptic in its parenthetical phrasing, but it earns its place as a behavioral caveat.

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 the return value (batch_run_id) and its purpose for progress tracking. Combined with plan limits and per-input-set execution semantics, an agent has enough to call it correctly. What is missing is guidance on the follow-up step (get_batch_status) and error/partial-failure behavior.

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%, and the inputs parameter already carries a full example mapping node IDs to URL arrays, so the schema does the heavy lifting. The description adds useful provenance (URLs must be uploaded via upload_file) but does not expand on flow_id or on ordering/format constraints for the arrays. Baseline 3 is appropriate here.

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 definition clearly states the action and resource (running a flow in batch mode with multiple input file sets) and defines what an input set is. It distinguishes itself from run_flow implicitly through 'batch mode' but never names the single-run sibling, so an agent must infer the split rather than being told. The upload_file reference clarifies the upstream dependency.

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?

It provides clear preconditions: file URLs must come from upload_file, and the account must be on the Starter plan or above. It also states a relevant exclusion — result locks from update_flow do not apply — which prevents an agent from gating the call unnecessarily. It stops short of explicitly contrasting with run_flow or get_batch_status for a single run versus polling.

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