create_work_items

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

The description adds significant behavioral context beyond annotations: atomicity (batch rejection), description format nuances (Markdown vs HTML, table styling, caption widget), validation behavior for enums and custom_fields, and the fact that returns new IDs. Annotations are limited (readOnlyHint false, destructiveHint false), so the description carries the full burden and delivers thoroughly, with no contradictions.

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 is relatively long but every sentence adds value. It is well-structured with clear logical flow: first states the core action, then uses newlines to segment important caveats (free-floating, atomicity, description format, validation). Minor redundancy could be trimmed but overall efficient and front-loaded with key points.

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 complexity (bulk creation with many optional fields, atomicity, format rules, validation needs), the description is remarkably complete. It covers creation procedure, post-creation step requirements, error implications, description format nuances, and points to sibling tools for enum resolution and document placement. The output schema exists to document return values, so that aspect is covered.

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?

Although schema coverage is 100%, the description adds operational meaning for each parameter: for 'items', it explains sub-field usage (description as Markdown only, enum validation, custom_fields key requirements) and links to list_work_item_enum_options for ID resolution. For 'dry_run', it explains preview behavior. The project_id parameter is straightforward. The description compensates for any schema terseness by providing actionable context.

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?

The description clearly states the tool creates 1-50 work items in one project in a single request. It explicitly distinguishes from a sibling tool by stating 'place into a document with move_work_item_to_document (this tool cannot)', which differentiates its purpose from related creation tools.

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 provides explicit guidance on when to use this tool: for bulk creation, and notes that items are created free-floating, requiring another tool for document placement. It warns about atomicity (one bad item rejects the whole batch), explains description format rules (Markdown only at creation, HTML later), and advises resolving enum IDs before use. It implies not to use for updates or single-item creation (covered by siblings). No explicit 'when not to use' but strong contextual cues.

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