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

The annotations already signal a non-read-only, non-destructive, idempotent state change, and the description does not contradict them. It adds little beyond the schema (the targetUserId format and lookup step), but for this simple action the task-facing behavior is adequately implied. It could have noted that success creates a pending request that requires acceptance, but this is a minor gap.

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?

One compact, front-loaded sentence with no filler; the action, parameter, and lookup prerequisite all appear in the first clause.

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?

With a single required parameter, full schema coverage, an output schema, and annotations covering safety semantics, the description plus structured data leave no practical gap. The explicit lookup-first instruction completes the workflow.

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 schema already documents targetUserId as the recipient's Mongo _id and tells the agent to use play_find_friend. The description restates this, adding a slightly clearer sequencing cue ('look them up first') but no new parameter meaning.

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 the specific action 'Send a friend request' and clearly identifies the resource ('another user'). It also names the target identifier and points to play_find_friend, which separates it from sibling request-management tools like play_accept_friend_request or play_cancel_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?

It gives an explicit precondition: look up the recipient with play_find_friend before sending. It does not enumerate exclusions such as 'do not use for accepting/declining/cancelling', but the verb and the named lookup sibling make the context clear.

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