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

Annotations only cover the safety profile (readOnlyHint=true, destructiveHint=false), and the description adds substantial behavior beyond them: cost model (never costs), incremental polling semantics, ownership by paying wallet with no account, and the details.expected signature challenge including both EIP-191 and ed25519 'solana:<pubkey>:<sig>' forms. This is the kind of auth-mechanics disclosure the annotations cannot convey.

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-loaded with 'FREE' and the purpose, then the return payload, then polling, then auth, then feedback. Efficient overall, but the closing paragraph about POST /feedback is scope drift into a different endpoint and the 'no individual reply' note, though brief, is not about invoking this tool.

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?

With no output schema, the description compensates by listing the returned fields. It covers cost, ordering (newest first), incremental polling, and the full ownership-proof handshake, which is everything an agent needs to call a 5-parameter authenticated read correctly.

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; the schema already documents id, nonce, since, signedAt, and signature. The description still adds meaning to the signature/nonce interplay by explaining the placeholder-signature-and-retry flow and the two signature encodings, which is more than the schema alone provides.

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 (read the mail an inbox received) and enumerates the exact return fields (from, to, subject, receivedAt, plain text, codes[], links[]). It explicitly ties itself to the sibling create_inbox ('how what you bought with create_inbox comes back to you'), so an agent can distinguish it from inbox_status, free_inbox, and the claim/storage reads without opening a 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?

Gives concrete operational guidance: poll with 'since' for incremental reads, and the fact that reading is free however often you poll. It names create_inbox as the producing counterpart. It does not, however, contrast against near-siblings like free_inbox or inbox_status, so the when-not-to-use case is left implicit.

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