list_work_item_links

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

The description reveals non-obvious behaviors: forward exposes role and suspect, back uses a Lucene query and returns None for role, with advice to recover via forward. This adds significant value beyond the readOnlyHint annotation, and there is no contradiction.

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 concise, with the main purpose front-loaded. It uses efficient phrasing and avoids unnecessary words. However, the second paragraph could be slightly more streamlined, but it remains clear and informative.

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 output schema exists, the description does not need to explain return values. It covers the essential behavioral differences between directions and the role attribute. It is sufficiently complete for a listing operation, though it could mention potential error scenarios or prerequisites.

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?

The schema covers 40% of parameters with basic descriptions (project_id, work_item_id, direction, page_size, page_number). The description adds deep behavioral meaning for the direction parameter, which is the most important one, and clarifies the difference between forward and back. This compensates for the moderate schema coverage.

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 'List a work item's outgoing or incoming links,' specifying the exact verb and resource. It distinguishes itself from sibling tools like create/update/delete work item links by focusing on listing, and explains the directional nuance.

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 explicitly says 'One direction per call' and explains the behavioral difference between forward and backward directions, including the Lucene query fallback and role behavior. It implicitly guides when to use each direction, though it doesn't explicitly list alternatives or exceptions.

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