deleteWorkItemsRelationship

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

Annotations declare destructiveHint=true, and the description meaningfully extends this with 'irreversible — data removed or overwritten by this call cannot be recovered through the API,' conveying data-loss consequence beyond the boolean hint. It also discloses a non-obvious behavioral quirk: dry_run previews are surfaced as error-flagged results, which the agent must interpret correctly. No contradiction 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?

Three sentences, front-loaded with the core purpose before the warning and tip. Each sentence earns its place, though the final dry_run explanation is somewhat verbose and partially overlaps with the schema's dry_run parameter description; the error-flag quirk it adds is genuinely new.

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?

With no output schema and a nested requestBody containing a large type enum, the description covers purpose, risk, and a safe preview path, while the schema handles parameter details. It omits what a successful response looks like and does not explicitly distinguish this relationship-slot delete from sibling tools that delete individual link entries (e.g., deleteLinkedWorkItems).

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 the schema fully documents all five parameters, including nuanced clarifications (projectId URL segment and case-sensitivity, WI-123 vs combined path, relationship slot vs link-entry ID, and dry_run redaction behavior). The tool description adds no parameter-specific meaning, which is acceptable under the baseline-3 rule since the schema carries the burden.

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?

States the verb and resource precisely: 'Deletes a list of Work Item Relationships.' The term 'list' signals batch scope, which loosely distinguishes it from single-relationship deletes, but it does not explicitly differentiate from sibling relationship tools (e.g., deleteLinkedWorkItems, patchWorkItemRelationships), leaving that distinction to the schema's parameter descriptions.

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 gives no explicit when-to-use vs alternatives guidance and names no siblings or exclusion conditions. It does imply a safe usage workflow by recommending `dry_run: true` before executing and warning that deletion is irreversible, which is meaningful operational guidance but not alternative-selection guidance.

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