unlink_tickets

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

With no annotations provided, the description fully carries the behavioral disclosure burden. It reveals that the tool removes all link kinds (dependency, related-to, duplicate-of), not just the dependency created by link_tickets; that it is idempotent (no error if never linked); and that unreadable or nonexistent uuids yield a 404. These are critical behavioral traits.

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 detailed but each sentence earns its place. It starts with the main action, then explains link-type behavior, idempotency, and error conditions, using concrete terms like 'dependency' and 'related-to'. No filler or repetition exists.

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 subtle behaviors (multiple link types, idempotency, 404 conditions) and the absence of annotations or an output schema, the description covers all aspects needed for correct invocation. It also points to `blocked_by` and `blocks` for existence checks, completing the contextual picture.

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 only task_uuid with a description (50% coverage). The description adds crucial meaning: 'Order does not matter — it finds the pair from either end,' clarifying that the two parameters are symmetric. It doesn't explicitly describe other_task_uuid's provenance, but the order-independence note compensates for the partial 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 opens with 'Remove the link between two tickets', a clear verb+resource statement. It further explains that order does not matter and that it removes ALL link types, distinguishing it from sibling link_tickets. This provides a specific and unambiguous purpose.

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 states when to use the tool: to remove a link regardless of which ticket is recorded as the blocker. It also gives a clear exclusion: 'this cannot be used to test whether a link exists; read `blocked_by` and `blocks` on the ticket for that,' pointing to alternative approaches.

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