submit_workflow

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

Beyond annotations, the description discloses key behaviors: it returns immediately (non-blocking), requires polling, needs auto-refill, and explains execution semantics (dependency order, parallel branches). This adds significant value beyond the structured annotations.

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?

Five sentences cover purpose, execution model, polling, billing, and schema reference. Every sentence adds unique value with no redundancy or fluff. The description is front-loaded with the core purpose.

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?

The description covers essential aspects: execution order, parallelism, polling interval, billing prerequisite, and schema reference. It lacks details about error handling or failure modes, but given the idempotentHint and output schema, it is largely sufficient for a competent agent.

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 description adds detailed structural requirements for the 'definition' parameter beyond the schema, specifying that it must include workflow_id and steps with id, tool, and inputs. This helps the agent construct valid input despite nested objects.

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 tool submits a multi-step workflow to the Botverse workflow engine, distinguishing it from sibling tools like cancel_workflow and get_workflow_status. The verb 'submit' and resource 'workflow' are specific and actionable.

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 context on when to use: for multi-step workflows with dependency ordering and parallel branches. It includes practical guidance like polling frequency and billing requirement, but does not explicitly mention when not to use or compare against other workflow-related tools.

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