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

Annotations already flag this as destructive and not read-only. The description adds meaningful behavioral context beyond those flags: 'Destructive on the social graph; both sides lose the connection,' which tells the agent the exact blast radius and impact. It does not address auth or reversibility, but the annotations carry the core safety signal.

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 three short sentences with no filler. It front-loads the action, then supplies the parameter source, then the destructive consequence. Every sentence earns its place.

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 single-parameter, destructive tool with an output schema and rich parameter documentation, the description is complete. It covers what the tool does, where the parameter comes from, and the social-graph consequence, leaving no important selection or invocation gap.

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 100% and the parameter description already explains that `friendId` is the friend record `_id` on the calling user's friends list, NOT the other user's id, and how to obtain it. The description repeats the provenance ('Pass `friendId` from play_list_my_friends') but adds no new parameter semantics, so the baseline of 3 applies.

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 opens with a specific verb and resource: 'Remove an existing friend connection.' It distinguishes this from pending-request operations by emphasizing 'existing friend connection,' which separates it from tools like play_cancel_friend_request, play_accept_friend_request, and play_decline_friend_request.

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 operational guidance by telling the agent to pass `friendId` from play_list_my_friends, which indicates the correct source and workflow. It does not explicitly name alternative tools for accept/decline/cancel, but the 'existing friend connection' framing implies the boundary; the schema's parameter description further clarifies that play_list_pending_friends is for accept/decline.

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