kanbn_remove_relation

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

No annotations are provided, so the description carries the burden. It discloses that omitting 'type' removes all relations, which is important behavioral context. However, it does not state whether the operation is reversible, whether it affects other tasks' relations (bidirectional edges), or any side effects on associated files. Given the tool is a mutation, this is a modest but not complete disclosure.

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?

Two concise sentences, both front-loaded with the core purpose and the key behavioral nuance (type filter). No filler words. Could arguably add a note about the dual source/target parameters, but it earns a 4 for its efficiency and clarity.

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 tool has four parameters, no output schema, and no annotations, so the description must carry more weight. It explains the type filter but fails to clarify the roles of 'task' and 'taskId' (which one is the source and which is the target), which is critical for correct invocation. It also does not mention whether relations are bidirectional or what happens if the task does not exist. Given the complexity of relation management, this is inadequate for a agent to safely call it without additional schema or annotation context.

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 all parameters with descriptions (100% coverage), so the description does not need to repeat them. The description adds value by clarifying the 'type' parameter's behavior (filtering removal) and implying that the 'task' and 'taskId' parameters distinguish source vs target. However, it does not explain the relationship between 'task' and 'taskId' (which is which), leaving a gap that the schema also does not resolve.

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 the specific action ('remove relation edge(s)') and the resource ('task'), and distinguishes it from its sibling 'kanbn_add_relation' and 'kanbn_set_relations' by focusing on removal. It also clarifies the optional type filter behavior, making the tool's scope unambiguous.

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 indicates when to use the tool (to remove relations) but does not explicitly contrast with alternatives like 'kanbn_set_relations' (which replaces all relations) or mention prerequisites (e.g., whether the task must exist). It provides no explicit when-not-to-use guidance, relying on the tool name to imply usage context.

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