history_listTaskInstances

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

No annotations provided, so description carries full burden. Documents specific return fields (name, assignee, endTime, duration, processInstanceId) which provides value, but omits pagination behavior, result limits, data retention policies, or query cost implications.

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 tightly constructed sentences with zero waste. Front-loaded with action verb. First sentence defines scope and filtering, second documents return payload. No redundancy.

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?

Effectively compensates for missing output schema by enumerating key return fields. Given zero parameter complexity and lack of annotations, provides sufficient context for tool selection and basic invocation.

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 4 for 0 parameters per calibration rules. Description references filtering dimensions (process instance, assignee, etc.) which implies query parameters, though schema defines none, creating implementation ambiguity.

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 'Query' with clear resource 'historic task instances'. Explicitly lists filterable dimensions (process instance, definition key, assignee, completion state) and distinguishes from siblings like history_listActivityInstances or history_listProcessInstances by focusing on task-level data.

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 archival usage via 'historic' and lists queryable fields, but lacks explicit guidance contrasting with runtime task_list for active tasks or when to use this versus other history_* siblings.

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