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

Discloses behavior well beyond the annotations: asynchronous execution requiring polling, and detailed re-run semantics (unchanged nodes retain results, except nondeterministic LLM/API/random-seed nodes which re-run). It also explains the locking escape hatch via update_flow(locked=true). The annotations only declare a non-readonly, non-idempotent, open-world mutation; the description adds the cache/regeneration model that matters for correct invocation.

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-loads the core action, then layers async polling, input handling, the batch alternative, and re-run semantics. The final re-run sentence is dense and slightly tangled, but each sentence carries necessary information; nothing is filler.

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, non-idempotent run tool with no output schema, the description supplies the completion-polling path, the input contract, the batch alternative, and the re-run/locking model. An agent has everything needed to invoke it correctly and interpret the asynchronous lifecycle.

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 coverage is 100%, so the schema already documents both parameters and the baseline would be 3. The description adds a cross-tool provenance hint ('file URLs from upload_file') for the inputs parameter that the schema does not state, which is a meaningful addition.

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 ('Execute a flow') and actively distinguishes itself from siblings by naming run_batch for multiple input sets and update_flow for locking. An agent can place this tool without opening any 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?

Explicit when-to-use guidance: poll get_flow(view="status") for completion, use run_batch for multiple input sets, provide file URLs from upload_file for flows with input nodes. It also explains the re-run condition, covering when and when-not to expect regeneration.

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