Operaton MCP

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

No annotations are provided, so the description must carry full behavioral disclosure. It successfully mentions the return structure (instance ID, state, definition info) which compensates for the missing output schema. It implies mutation via 'Start,' but lacks crucial BPMN-specific context such as idempotency guarantees, synchronous vs asynchronous execution behavior, or what happens if the definition key is not found.

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 consists of three efficient clauses with zero waste. The primary action ('Start a new process instance') is front-loaded, followed by the lookup mechanism ('by definition key'), optional inputs, and return values. Every clause 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 the high complexity of BPMN process instantiation and the complete absence of annotations and output schema, the description provides the minimal necessary context (key-based lookup, return values). However, it omits error handling, transaction boundaries, and validation behavior that would be expected for a production-grade workflow engine.

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?

With zero parameters in the schema, the baseline score is 4. The description attempts to compensate for the empty schema by documenting implied parameters ('business key and typed variables'), adding semantic meaning that the structured schema fails to provide. However, this creates a slight tension with the empty schema declaration.

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?

Specific verb ('Start'), specific resource ('process instance'), and precise mechanism ('by definition key'). The phrase 'latest version' clearly distinguishes this from specific-version deployment tools, and the 'by definition key' pattern implicitly distinguishes it from the sibling 'processInstance_startById' tool.

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 by specifying the 'definition key' lookup mechanism, suggesting when to use this (when you have the key and want the latest version) versus the ID-based sibling. However, it fails to explicitly state 'use processInstance_startById instead if you have the ID' or mention prerequisites like deployment existence.

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