Create TOCA Workflow

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

Annotations indicate readOnlyHint=false, destructiveHint=false, and idempotentHint=true. The description adds the 'durable' and 'transactional outbox' context, which hints at persistence and eventual consistency. It does not contradict annotations, but could elaborate more on the effects of creating a workflow, such as side effects or state changes. However, with annotations covering safety (non-destructive, idempotent), the description adds reasonable context.

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 a single sentence, extremely concise, and front-loaded with the main purpose. It wastes no words and gives essential context about durability and transactionality. This is appropriately sized for a JSON description.

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 the complexity (7 parameters, nested steps array) and lack of output schema, the description is too sparse. It does not explain what the tool expects for steps structure, how idempotency works, or what the return value looks like. The annotations help with safety, but the description misses crucial operational details such as default behavior, limits, or required relationships between parameters. An agent would struggle to invoke this correctly without more context.

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 must compensate, but it does not explain any of the 7 parameters. Required fields like routeId, definitionId, steps, idempotencyKey, correlationId, etc., are not described beyond the schema's basic type constraints. The description gives no semantics for parameters, making it hard for an agent to know what values to provide. This is a significant gap.

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 states it creates a durable tenant-scoped workflow using an existing engine and transactional outbox. It clearly indicates the action (create) and resource (workflow), and distinguishes from siblings like get, advance, execute by the creation-focused purpose. However, it could be more specific about the type of workflow or the context (TOCA) beyond the name.

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 implies usage in the creating workflows, but does not explicitly state when to use this tool vs alternatives like toca.execute or toca.workflow.advance. There is no explicit when-not-to-use guidance. Given the sibling list, a clear guideline would help, but it's not entirely missing.

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