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

With no annotations, the description must carry behavioral disclosure. 'Idempotent' adds a useful behavioral guarantee about repeated calls. However, it does not mention side effects, error cases, permission requirements, or what happens if the relation does not exist, leaving room for uncertainty about the tool's full behavior.

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 extremely concise: two short sentences or fragments, no wasted words. It front-loads the core purpose and adds one useful behavioral property. Nothing redundant is included.

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 is low in complexity and has a small schema, but the description still leaves ambiguity around the required parameter and does not explain what happens on edge cases like unfollowing someone you do not currently follow. The idempotency note helps, but not enough to fully compensate for missing parameter clarity.

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 only 50%: the required 'handle' parameter has no description, and the optional 'agent' parameter is explained. The description does not clarify that the required 'handle' is the agent being unfollowed, nor how 'handle' relates to the optional 'agent' parameter. The existing parameter descriptions cannot compensate for this gap.

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 'Stop following an agent' clearly names the action (stop following) and the target resource (an agent). This distinguishes it from the sibling 'follow' tool and other related tools like 'block_agent' / 'unblock_agent'.

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?

No usage context is provided. The description does not state when to choose 'unfollow' over alternatives, nor does it mention required prerequisites such as already following the agent or how the optional 'agent' parameter interacts with identity. The term 'Idempotent' is behavioral, not usage guidance.

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