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

Annotations already declare readOnly=false, openWorld=true, idempotent=false, destructive=false, so the safety profile is largely covered. The description adds material context beyond them: a two-step unsigned/signed handshake, the fact that no key is held, the exact op vocabulary, and that the wallet defaults to the account's when signed in. It does not describe what the read returns or error/failure behavior for rejected signatures.

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?

It is front-loaded with what the tool is and what it returns, then moves into the op vocabulary and the signing workflow. Nearly every clause carries information, though the phrasing 'No op reads it' and the unquoted `sign_this` reference are terse enough to require re-reading.

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-parameter mutation tool with zero schema description coverage and no output schema, the description covers the read shape, the full op set, the signing handshake, the wallet default, and the absence of key custody. The remaining gap (precise meaning of `at`) is narrow relative to the complexity involved.

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 description coverage is 0% across 5 parameters, so the description must carry the load. It does well for `op` (enumerating ask|accept|decline|cancel|remove|block|unblock, which the schema does not encode as an enum) and clarifies `other`, `signature`, and that `wallet` defaults to the account's. However `at` is never explained beyond appearing alongside `sign_this`, and `sign_this` is not actually a parameter, leaving the handshake input semantics partly obscure.

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 specific resource (a wallet's public friends list, online/game status, join link, plus the `buddies` agents field) and states that an op-less call reads it while an `op` performs a mutation. It is specific but dense and does not distinguish itself from siblings such as `ask` or `buddy`, which plausibly overlap with the `ask` op and the friends concept.

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 concrete procedural guidance: call unsigned to get `sign_this` + `at`, sign locally with EIP-191 personal_sign, then call again with `at` + `signature`; and it notes that when signed in at /mcp/account/ the wallet defaults to the account's and the op applies immediately. What is missing is when to prefer this tool over the sibling `ask` or `buddy` tools, so no explicit alternative routing is provided.

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