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

Annotations already mark the operation as destructive and idempotent. The description adds meaningful behavioral context beyond those hints: it can only cancel requests the calling user initiated, and it targets the friend record on the user's own friends list, not the other user's id. This helps the agent avoid common misuse.

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 focused sentences with no filler. The action and the key disambiguation are front-loaded, and the parameter guidance is placed exactly where it is relevant.

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, output-schema-bearing mutation tool with annotations covering destructiveness and idempotency, the description is complete. It identifies the target, the required parameter, how to source that parameter, and the boundary of what it can cancel.

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%, so the baseline is 3. The description adds value by emphasizing that friendId is the friend record on the caller's own friends list and specifically the one the caller initiated, and by directing the agent to the sibling list tools that produce this value. This goes slightly beyond the schema's own wording.

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 states a specific verb ('Cancel') and resource ('a friend request the calling user previously sent'), and clarifies scope by noting it must be a request the calling user initiated. This clearly distinguishes it from siblings like play_accept_friend_request, play_decline_friend_request, and play_remove_friend.

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 the tool applies (only to requests the calling user previously sent) and the parameter description points to play_list_pending_friends and play_list_my_friends as sources for the required friendId. It does not explicitly state when NOT to use this tool versus decline or remove, but the caller-initiated qualifier largely disambiguates.

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