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

Annotations mark this destructive/openWorld, and the description goes well beyond that, disclosing that a real person is emailed, that confirmation is mandatory, that unregistered emails become invitations, and that the email path returns a deliberately neutral result for privacy. These are exactly the consequences an agent needs before invoking a non-idempotent, outward-facing action.

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?

Front-loads verb+resource, then the mandatory confirmation gate, then parameter constraints, then edge-case behavior. Four tight sentences, none wasted, in a sensible priority order.

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 send tool with no output schema, the description covers the action, required human confirmation, parameter constraints, and the two edge behaviors (invitation fallback, privacy-neutral response). An agent has everything needed to call it safely.

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, but the description adds meaning beyond the schema: it clarifies the email path can trigger an invitation and always yields a neutral result, and reinforces the confirmation semantics of confirmed. That is genuine added semantic value over the field descriptions.

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?

States a specific verb+resource ('Send a friend request') and the two targeting mechanisms (user_id or email), so the agent knows exactly what the tool does. It does not, however, differentiate itself from related siblings like friend_request_resend or friend_request_accept, leaving the routing to inference.

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?

Gives a strong, actionable precondition: confirm the recipient with the user first and pass confirmed=true only after agreement, plus the 'exactly one of user_id or email' rule. It stops short of naming alternative tools (e.g. resend for an existing request), so it lacks explicit when-not guidance.

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