list_work_items

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

Beyond the readOnlyHint and openWorldHint annotations, the description adds detailed behavioral context: pagination with cursor, default per_page, total_count semantics, sparse fieldset behavior (null means not requested), and external system filtering. No contradictions with annotations.

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 well-structured with clear sections (purpose, usage guidance, args, returns) and is front-loaded with core purpose. While lengthy, each sentence adds value, and the bullet points improve readability. Minor redundancy in field descriptions but overall efficient.

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 tool's complexity (9 parameters, pagination, filtering, sparse fields, external system integration) and the presence of an output schema, the description covers all necessary aspects: input parameters, return structure (results, total_count, cursors), and behavioral nuances. It is sufficiently complete for agent usage.

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?

Despite low schema description coverage (11%), the description provides extensive parameter details: pql examples, order_by syntax, per_page range, cursor usage, expand comma-separated relations, fields list with null behavior, and external_id/source pairing. This adds significant meaning beyond the schema.

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 lists work items with optional PQL filtering, and distinguishes it from siblings by explaining how to scope results (workspace-wide vs single project) and how to resolve UUIDs using other list tools. This provides specific verb+resource scope differentiation.

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 omit or include project_id, and instructs the agent to call relevant list tools for UUID fields. It also references get_pql_reference for complex queries. However, it does not explicitly differentiate from search_work_items or other filtering tools, leaving some ambiguity.

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