history_listVariableInstances

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

Discloses return payload structure (variable name, type, value, activity instance) which partially compensates for missing output schema. Lacks essential behavioral details expected when no annotations present: read-only safety, pagination behavior, result limits, or performance characteristics of history queries.

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 information-dense sentences with efficient structure. First sentence establishes functionality and filters; second describes return values. No filler content, though front-loading could emphasize the read-only nature given missing annotations.

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?

Adequate coverage of return values given no output schema exists, but incomplete for a history query tool: missing pagination controls, maximum result limits, sorting options, and explicit safety guarantees that annotations would normally provide.

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?

Provides semantic meaning for filtering criteria (process instance ID, variable name) that compensate for the completely empty input schema. Baseline 4 maintained for zero-parameter tools, though the description references parameters not formally declared in the schema structure.

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?

Clear verb (Query) and resource (historic variable instances) with specific filters mentioned (process instance ID, variable name). Distinguishes from siblings by specifying 'historic' scope, though could better contrast with runtime variable tools like processInstance_getVariables.

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 guidance on when to use this versus runtime variable retrieval (processInstance_getVariables) or other history query tools. The 'historic' qualifier provides only implicit context without specifying use cases involving completed versus active process instances.

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