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

Annotations only flag it as open-world, idempotent, non-destructive and not read-only; the description goes far beyond that by disclosing the pricing model ($0.005 USDC on Solana via x402), the exact MCP payment handshake (first call returns PaymentRequired, retry with _meta["x402/payment"]), the payer-of-record-equals-sender rule, free rejection of undeliverable sends, opaque ciphertext storage, and 30-day retention. These are precisely the operational traits an agent cannot infer from annotations.

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?

The core action and payload shape are front-loaded, followed by prerequisites, pricing, and the HTTP equivalent. The single dense paragraph carries a lot of value per clause, though the x402/payment mechanics and endpoint URLs could be split into a separate sentence for easier scanning.

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 paid, open-world mutation with no output schema, the description covers everything needed: prerequisites (declared mailboxes, payer identity), the payment dance, failure modes (free refusal before payment), retention, and a fallback HTTP endpoint. Nothing an agent needs to invoke it successfully is missing.

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 baseline is 3, but the description adds real meaning: the mailbox must be a declared Ed25519 pubkey (declared at POST /toll/a2a/mailbox/declare), the payer of record must equal the 'from' mailbox, and the signature is defined over the a2a-msg/v1 payload. It reinforces rather than merely repeats the constraint of 'exactly one of to / to_handle'.

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 opens with a specific verb and resource: 'Send one 1:1 direct message through the A2A ciphertext relay', and immediately disambiguates with '1:1 DM only'. It makes the tool's scope unmistakable relative to the rest of the catalogue, where no sibling overlaps.

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 names the alternative path explicitly ('Free pre-check at POST /toll/a2a/send/preflight') and states the constraint that only 1:1 DMs are supported, plus that undeliverable sends are refused free before payment. What's missing is a clear statement of when an agent should skip this tool entirely (e.g. group/multicast cases routed elsewhere), so it falls short of a full when/when-not treatment.

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