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

Annotations declare readOnlyHint=true, but the description states the tool writes a locked, immutable notarization to the public IOTA ledger ('cannot be changed or transferred and its deletion is locked until 2106') and charges $0.01 USDC per call. Creating irreversible on-chain state and spending funds is not a read-only operation, so an agent told this tool is side-effect-free could invoke it without the confirmation a paid, permanent write warrants. This is a direct annotation contradiction.

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?

Well front-loaded: purpose and privacy guarantee come first, then returns, then use cases, then cost and sample. It is long (~130 words) and carries payment/onboarding detail an agent may not need on every call, but each sentence does carry actionable information, so the length is mostly earned.

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 fully carries the burden: it enumerates the return payload (object id, transaction digest, ledger time, explorer links), the storage model (hash only, immutable, deletion locked), the cost and payment rail (x402 USDC on four chains), and the sibling to use for later verification. Nothing material is left for the agent to guess.

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, but the description adds real semantic value beyond the schema: it tells the agent that only the SHA-256 digest is persisted and 'never your content', which changes how an agent reasons about sending sensitive text or URLs. The three input modes (text, hash, url) are restated at a level that confirms the schema's intent rather than merely repeating it.

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?

Opens with a concrete verb+resource+network: 'Proof of existence on the IOTA mainnet: send text, a SHA-256 hash or a URL and get a tamper-proof timestamp.' It explicitly distinguishes itself from its nearest sibling by stating 'Check later with iota-verify', so an agent can route between notarize and verify without opening either 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 when-to-use triggers ('contracts, invoices, AI outputs, datasets, web page evidence or audit logs'), names the alternative for the follow-up action (iota-verify), and provides a runnable example input as a free sample. There is no ambiguity about when this tool, rather than a verification or hashing sibling, is the right call.

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