create_work_item_links

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

The description is exceptionally transparent about behavior beyond annotations: atomicity, role/target existence validation, defaulting behavior (target_project_id defaults to source, revision pins else HEAD), suspect flag meaning, entire batch rollback on duplicate, and the critical phantom success caveat where a new same-role link reports created but is not persisted on document-attached sources. This goes far beyond the simple write hints in 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 front-loaded with the purpose, then logically organized into validation/spec, rollback behavior, and phantom success warning. It is dense but each sentence provides critical operational detail. It could be slightly tighter, but the structure and direct information justify a high score.

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?

For a complex batch creation tool, the description covers all essential behavioral aspects: atomicity, validation, defaults, rollback, output ids (delete-path ids), and a non-obvious phantom success scenario. An output schema exists to cover return values, and the description complements it thoroughly. No significant gaps remain.

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?

Schema description coverage is 100%, so baseline is 3. However, the description adds meaningful semantic detail for parameters: target_project_id defaults to source, revision pinning vs HEAD, suspect flags re-review, and duplicate role+target causing batch rollback. These enrich understanding beyond the plain schema descriptions, though it doesn't fully detail every parameter's edge cases.

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 opens with 'Create 1-50 outgoing links from one source work item, atomically' – a specific verb, resource, and scope. It clearly distinguishes this from sibling link/attachment tools (list/delete/update_work_item_links) by focusing on creation and batch atomicity.

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 clear context: atomic batch creation, validation before writing, and rollback on duplicate role+target. It tells the agent to re-query list_work_item_links before retrying and to verify with list_work_item_links, but it does not explicitly contrast with alternatives like update_work_item_link or delete_work_item_links, so it falls short of full when/when-not guidance.

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