notary_notarize

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

With no annotations, the description carries the full burden and does well: it discloses that the server independently verifies the on-chain payment, that a base64 Ed25519 NEP-413 binding signature over a specific message format is required, and that the call returns a job_id. It omits failure behavior (invalid/duplicate tx_hash, insufficient amount) and idempotency, which for a payment-gated mutation matters.

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?

Purpose and precondition are front-loaded, and the flow summary at the end closes the loop cleanly. The embedded multi-line signature template bloats the middle, but it is load-bearing information rather than 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 payment-gated, multi-step tool this covers prerequisites, binding requirements, and the handoff to verification, and an output schema exists so return values need little prose. The main gap is the four undocumented optional parameters (agent_sig, agent_pubkey, artifact_uri, metadata), which matter for an artifact-submission call.

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%, so the description must document the 8 parameters itself. It gives real meaning for tx_hash, payer_account, bind_sig (including the exact signed message template) and implicitly work_hash, but leaves metadata, agent_sig, agent_pubkey and artifact_uri entirely unexplained in both schema and description — half the surface is still opaque.

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 concrete verb+resource ('Submit a work artifact for on-chain notarisation') and scopes it to the NEAR_DIRECT payment path, which implicitly separates it from notary_free and notary_notarize_paid. The placement as 'Step 3 of the notarisation flow' further pins down its role, though the paid/free siblings are never named explicitly.

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 an explicit prerequisite (pay the notary_quote amount to the sink account first), the ordering of the flow (quote -> pay -> notarize -> verify), and names notary_verify as the polling follow-up. It does not, however, say when to choose this over notary_notarize_paid or notary_free, so the alternative selection remains inferred from the payment-path parenthetical.

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