remove_relation

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

With no annotations, the description carries the full burden and does well by disclosing the non-obvious requirement that the kind must match the original relation. It also points to get_task for verifying current state. It does not mention error behavior or side effects, but for a simple relation removal this is reasonably transparent.

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 short sentences with no fluff. The main purpose is front-loaded, and each subsequent sentence adds necessary behavioral or reference information.

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?

For a simple operation with three parameters and no output schema, the description covers the essential invocation requirements. It tells the agent what to do, what constraint applies, and where to find valid values and current state. Minor gaps like default behavior or error cases are not critical for this tool.

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 coverage is 0%, so the description must compensate. It explains the meaning and constraint of relation_kind ('kind has to match... see add_relation for the list') and clarifies the task parameters by describing the operation as between two tasks. The task_id and other_task_id are self-explanatory from names and types.

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 'Remove a relation between two tasks,' which is a specific verb-resource pairing. It is immediately distinguishable from the sibling add_relation, and the second sentence reinforces that distinction by pointing to add_relation.

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 clear context: the relation kind must match the one used at creation, and get_task can be used to inspect current relations. It names both add_relation and get_task as alternative/reference tools, though it does not explicitly state 'use this only when a relation exists.'

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