processDefinition_getMigrationCandidates

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

No annotations provided, requiring description to carry full behavioral disclosure burden. It explains return structure categories and optional variable-checking logic. However, lacks safety profile disclosure (read-only vs. side effects), error handling specifics, or performance characteristics for the comparison operation.

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 efficient sentences front-load critical information: first defines core comparison and return types, second covers optional variable-checking behavior. No redundant text or filler despite being description-only with no title.

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?

Absence of output schema is partially mitigated by description detailing return categories (auto-mappable pairs, unmapped, new). However, critical incompleteness: empty input schema combined with description's reference to 'supplied instance IDs' leaves invocation context ambiguous. Does not explain how source/target process definitions are identified given zero schema properties.

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?

Baseline for 0 parameters is typically 4, but description confusingly references 'supplied instance IDs' implying input parameters exist, while schema is strictly empty. This creates ambiguity about how source/target definitions and optional instance IDs are specified, failing to clarify the empty schema interface.

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 specific comparison operation ("Compare source and target process definition activities") and enumerates return categories (auto-mappable pairs, unmapped source activities, new target activities). Distinguishes from sibling migration execution tools (e.g., migration_executeBatch) by focusing on analysis/candidate identification, though could explicitly clarify this precedes actual migration.

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?

No explicit when-to-use or when-not-to-use guidance relative to migration_* siblings (e.g., migration_generatePlan, migration_validatePlan). Does not specify prerequisites for providing source/target definitions despite empty input schema. User must infer appropriate context solely from the tool name.

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