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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds one genuinely useful non-obvious consequence — that favorites survive the unfriend — but says nothing about whether the change is reversible, whether it requires the target to exist, or what a not-a-friend call returns.

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?

A single short sentence with the action front-loaded and the notable side effect in parentheses. No filler.

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 mutation, annotations carry the destructive/idempotent semantics and the parenthetical covers the main surprise. What's missing is anything about the handle argument and about failure modes, leaving the definition just adequate.

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?

There is one required parameter (handle) with 0% schema description coverage, and the description says nothing about it. In a federated context the handle format (local vs. @user@domain) is a real ambiguity the description could resolve but doesn't.

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 gives a clear verb+resource ("Remove a mutual friendship") and the word "mutual" signals a symmetric relationship rather than a one-way follow, which helps separate it from siblings like unfavorite or delete_post. It doesn't explicitly name a sibling or clarify how it differs from a hypothetical block/unfollow, so it stays just below a 5.

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?

Usage is only implied: an agent can infer this is the inverse of friend_invite/accept_invite, but the description never states when to call it versus those siblings or what prerequisites exist. No exclusions or alternatives are given.

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