kiwi_delete_entity

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

With no annotations, the description carries the full burden of behavioral disclosure, and it does so explicitly: 'DESTRUCTIVE' is highlighted, and the ORM remove mechanism is described, making clear that matching records are permanently deleted. The 'id__in' example also hints that bulk deletion is possible, which is critical behavioral context. It does not mention permissions, rollback, or cascading effects, but the destructive warning is the most important safety disclosure an agent needs.

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 compact and front-loaded: it opens with the core purpose, immediately warns 'DESTRUCTIVE', and then gives necessary examples. Every sentence earns its place; there is no filler or repetition of the schema.

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 no annotations and no output schema, the description covers the essential aspects: what the tool does, the parameters and their formats, and the destructive nature. It does not mention return values, auth requirements, or error behavior, but for a simple delete tool the examples and warning provide enough context for an agent to invoke it correctly. The only notable gap is the absence of an exhaustive model list, but the 'e.g.' phrasing appropriately signals extensibility.

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 0%, so the description must compensate, and it does. It explains that 'model' receives an ORM class name and provides concrete examples ('TestCase', 'TestRun', 'TestExecution', 'Tag'). It defines 'query' as an ORM filter dict and gives two realistic examples: a single id lookup and an id__in list. This transforms two bare schema properties into actionable parameters.

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 a specific action ('delete'), the resource ('<Model>'), and the mechanism ('calls <Model>.remove with the given ORM filter dict'). It identifies itself as 'Generic delete', which distinguishes it from specialized sibling tools like kiwi_delete_test_case and kiwi_delete_test_run. The examples of valid model names further clarify the intended scope.

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 does not explain when to use this generic delete versus the specialized delete tools for test cases and test runs. While 'Generic' implies it covers multiple models, it gives no explicit guidance about when to prefer it over siblings or whether the specialized tools should be used for TestCase/TestRun. As a result, an agent must infer the correct choice from the name alone.

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