THE KEYSTONE. Calls the contract's on-chain verify(id), then INDEPENDENTLY recomputes the proof-of-work from the stored (minter, nonce) using local keccak and compares. Two machines, one truth. Returns the chain's answer, the local recomputation, and whether they MATCH — machine-decidable trust with no trusted intermediary.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | token id to verify |
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 the on-chain call, the independent local recomputation using keccak, and the returned triple of chain answer, recomputation, and match status. It does not mention error behavior for nonexistent ids, but the core verification behavior is clearly exposed.
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 functional content is compact and the mechanical steps are front-loaded, but phrases like 'THE KEYSTONE.' and 'Two machines, one truth.' are pure flourish that do not help an agent select or invoke the tool. They add noise without earning their place.
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 one-parameter tool with no annotations and no output schema, the description is nearly complete: it explains the verification flow and the shape of the return value. The only notable omission is behavior for invalid or nonexistent token ids.
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?
The schema already fully documents 'id' as the token id to verify (100% coverage). The description confirms id is passed to on-chain verify(id) but adds no new semantic detail beyond what the schema provides, so the baseline of 3 applies.
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 states a specific verb and resource: it calls on-chain verify(id), recomputes proof-of-work from (minter, nonce), and compares results. It clearly distinguishes itself from simpler verification siblings by emphasizing independent local recomputation and the match comparison.
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?
The phrase 'machine-decidable trust with no trusted intermediary' implies this is for trustless verification, but the description never explicitly says when to use this tool over alternatives like koine_verify or nonce_mine. There are no exclusions or conditional routing cues.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The koine_ and nonce_ prefixes cleanly separate two distinct collection workflows, and within each prefix every tool addresses a unique action or resource. Even the two verify tools are easily distinguished by collection prefix and their exact verification behavior.
Tool names share a clear collection-prefix snake_case scheme, making grouping and selection predictable. However, not every name follows the same verb_noun form—info, census, spec, listings, and provenance are noun-style while mine, get, list, and verify are verb-style—so the pattern is consistent but not perfectly uniform.
13 tools is well-scoped for a server covering two distinct on-chain art collections with read, discovery, verification, and minting workflows. Each tool maps to a real operation, with no obvious filler or redundant entries.
The NONCE half covers the full lifecycle well: spec, mine, mint_packet, verify, info, census, and get_piece. The KOINE half covers discovery, provenance, listings, and verification, but the only acquisition route is external Seaport fulfillment, with no KOINE purchase or fulfillment packet equivalent to nonce_mint_packet—a minor but real gap.