delete_relation

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

Annotations already indicate destructiveHint=true and idempotentHint=true. The description adds that deletions are idempotent and that ambiguous selectors cause failure, but does not disclose other behavioral traits such as permissions needed or cascading effects. The added value is modest beyond 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 cover the core purpose, locator types, and an important behavioral constraint. No redundant information. Every sentence adds value.

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?

The description covers primary use cases but does not explain the direction parameter in detail (e.g., what 'either' means) or provide guidance on when to use relation ID vs triple. Since an output schema exists, the lack of return value info is acceptable, but more parameter guidance would improve completeness.

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?

While schema coverage is 100%, the schema descriptions are minimal (e.g., 'a string that will be trimmed'). The description compensates by explaining that source/target use endpoint locators supporting raw, issue, document, and card, and that direction semantics mirror create_relation. This provides meaningful guidance beyond the schema.

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 'delete one concrete relation' and specifies two identification methods (by relation ID or by association/source/target triple). It distinguishes from sibling tools like delete_association and delete_issue_relation by focusing on generic relations and referencing create_relation for direction semantics.

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 provides context on how to use the tool (by ID or triple) and mentions ambiguity failure, but does not explicitly tell when to prefer this tool over alternatives like delete_association or delete_issue_relation. It assumes the agent knows the difference between relations and associations.

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