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

Annotations declare readOnlyHint=false and destructiveHint=false; the description adds genuinely new behavioral context the annotations don't carry — a two-phase unsigned/sign/resubmit auth flow and 'Nothing here holds a key'. That is real value beyond the annotation flags. It does not explain what remove/block actually destroy, which is the remaining 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?

Very compact and front-loaded, with the read semantics stated before the op list and the signing procedure last. The style is fragmentary ('asks either way'), which costs a little clarity, but no sentence is 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 5-param, no-output-schema, mutable tool, the description covers the ops, auth handshake, and safety note ('holds no key'). It stops short of describing what a successful call returns or what remove/block do to existing state, which an agent would want before invoking mutations.

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 0%, so the description must compensate, and it largely does: `op` is fully enumerated, `other` is defined ('the wallet it names'), and `at` and `signature` are explained by the signing loop. `wallet` is only implied by the possessive framing. This is strong compensation for an undocumented schema.

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 names a concrete resource (a wallet's friends list, buddies, inbound/outbound asks) and enumerates the mutation verbs (ask, accept, decline, cancel, remove, block, unblock). It is terse and telegraphic, but an agent can distinguish the read mode ('No op reads it') from the write ops without opening the schema.

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 explicit procedural guidance: call with `op` unsigned to receive sign_this + at, sign locally with EIP-191 personal_sign, then call again with at and signature. It also notes buddies need 'no ask needed'. It lacks explicit sibling routing, but the workflow conditionality is unusually clear.

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