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

No annotations exist, so the description carries the full behavioral burden for what is a social write operation. It does not say whether sending is idempotent, what happens if the agent is already a friend, or what error occurs when no request is pending to accept.

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 short sentence, front-loaded with the primary action and the secondary mode appended cleanly. No filler and no redundancy.

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 tool this is close to adequate, but with no annotations, no output schema, and an unresolved handle ambiguity across the two modes, the agent lacks the detail needed to call it correctly in the accept case.

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% with the handle described as 'Agent handle', so the structured field does the documentation work. However, the description leaves a real ambiguity unresolved: whether handle is the target of the outgoing request or the sender of the pending one.

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 (send/accept a friend request) and the resource (friend request), and even discloses the dual mode. It does not name or contrast with siblings like unfriend or my_friends, so the agent gets no explicit differentiation.

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 phrase 'or accept one that is waiting for you' implies a second usage mode, but the agent is never told how to detect a pending request, nor that unfriend/my_friends are the alternatives for the related operations. Usage is only implied.

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