link_work_items

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

Beyond annotations (readOnlyHint=false), description adds idempotency, preservation of existing children, and dry_run default, giving full behavioral clarity.

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?

Three concise sentences cover purpose, replacement, idempotency, resolution, and dry_run without 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?

Despite no output schema, description covers prerequisites, behavior, and parameter semantics completely for a mutation tool with dry_run support.

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?

All parameters are described with additional context beyond schema: parent requires resolution, child items can be Issue or Epic, dry_run explains default and user confirmation requirement.

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?

Description clearly states it attaches work items as children of a parent epic, specifying verb, resources, and distinguishing itself as the GitLab 17+ replacement for add_issue_to_epic.

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?

Provides guidance on resolving GIDs via get_work_item_id and dry_run usage, but could more explicitly contrast with siblings like add_linked_item.

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