Operaton MCP

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

No annotations provided, so description carries full burden. Adds valuable behavioral constraints: 'active' status filter (suggesting it won't return completed instances) and specific return fields documented since no output schema exists. Missing: error behavior (404 vs null), auth requirements, and rate limits.

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?

Two sentences with zero waste: first declares operation and subject, second lists return payload. Every word earns its place; front-loaded with essential action and scope.

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?

Good given constraints: documents return fields to compensate for missing output schema and distinguishes 'active' scope. Deducted one point because error conditions (instance not found, not active) and the ID parameter location (path vs body) remain unspecified, which is critical for a lookup tool.

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?

Input schema has 0 parameters (baseline 4 per rubric). Description adds critical context by mentioning 'by ID', indicating the intended lookup mechanism even though the parameter is not declared in the schema (likely a path parameter or schema omission).

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 'Retrieve' with resource 'process instance' and scope 'single active'. Implicitly distinguishes from sibling 'processInstance_list' (many vs one) and 'history_listProcessInstances' (active vs historical) via the 'active' qualifier, and from 'processInstance_getVariables' by listing specific identity fields returned (id, definitionKey, etc.).

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?

Implies usage when you have a specific ID, but provides no explicit guidance on when to use alternatives like 'processInstance_list' for searching, 'history_listProcessInstances' for completed instances, or error handling when the ID is not found.

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