KGLD gold-token reserve proof: custody vs supply, auditor report hash, human verification by email
Scored across 3 tools
get_attestation (auditor's report) and get_reserve (issuer's tally) both concern reserves and could be briefly confused at a glance, but the descriptions sharply distinguish auditor vs issuer perspectives and cross-reference each other. request_verification is clearly distinct as an out-of-band email action.
All three names follow a consistent snake_case verb_noun pattern: get_attestation, get_reserve, request_verification. The verb shift from get_ to request_ is semantically appropriate rather than a convention break.
Three tools is lean but well-scoped for a narrow, single-purpose attestation server; each tool earns its place (report, current figures, verification request). It sits at the low end of the ideal range but no obvious tool is redundant or missing.
The surface covers the core lifecycle: fetch the auditor's proof, fetch current reserve/supply, and request independent verification. Minor gaps exist (no attestation history or auditor-domain lookup, the latter explicitly out of scope), but core verification workflows are not dead-ended.
Independent auditor's proof-of-reserve report for KGLD: public PDF URL, SHA-256, as-of date, attested custody (troy oz), auditor name; active token contract addresses with block-explorer links; and independentChecks — how to verify without trusting this server (hash the PDF, read totalSupply on-chain, compare). Start here for any 'is KGLD really backed' question. / 독립 감사 보고서 주소·해시·기준일·수탁량, 컨트랙트 주소·탐색기, 서버 밖 검증 방법.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does unusually well: it discloses the trust model and the out-of-band verification path (hash the PDF, read totalSupply on-chain, compare). It is implicitly a read-only report, but permissions, caching/freshness, and rate-limit behavior are not stated.
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 the resource and then a field-by-field inventory that doubles as return-value documentation, so the density is largely earned. The bilingual duplication adds length without adding information, which keeps it out of the top band.
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 and no parameters, the description fully compensates by enumerating the returned fields and explaining how to verify them independently. An agent asking 'is KGLD backed' has everything needed to call and interpret this tool.
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 tool takes zero parameters, so per the rubric the baseline is 4; there is nothing for the description to disambiguate and the schema is trivially complete.
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 resource with qualifiers: 'Independent auditor's proof-of-reserve report for KGLD', and enumerates the exact payload (PDF URL, SHA-256, as-of date, custody in troy oz, auditor name, contract addresses). It clearly differs in substance from get_reserve/request_verification, though it never names those siblings explicitly, so an agent must infer the boundary.
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?
Provides a concrete entry-point rule: 'Start here for any is KGLD really backed question,' which tells the agent when to reach for this tool first. It offers no explicit exclusions or named alternatives, so the when-not side is left to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
KGLD current reserve: custody gold weight (g, troy oz), on-chain total supply, mintable allowance. Issuer's own tally (KorDA); the auditor's assurance covers only up to get_attestation.asOf. Verify supply on-chain via get_attestation.contracts. / KGLD 현재 준비금·발행량·발행 가능량. 코르다 자체 집계.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses data provenance (issuer's own tally), units, the assurance limitation, and directs verification to a sibling tool. It does not discuss auth, rate limits, or exact output shape, but these are less critical for a zero-parameter read-only tool.
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 description is compact, front-loaded with the tool's core purpose, and every sentence adds value. The Korean duplicate is quick and relevant for the stated locale, and the important caveat about auditor assurance appears early rather than buried.
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?
This is a zero-parameter, read-only tool with no output schema, and the description covers its result contents, units, provenance, limitations, and verification path. There is nothing an agent needs to call it correctly that 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?
The input schema has zero parameters, so the baseline for this dimension is 4. The description still adds semantic context by listing the fields an agent should expect in the result, which is more useful than an empty schema alone.
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 ('get') and resource ('reserve'), then enumerates exactly what is returned: custody gold weight in grams and troy ounces, on-chain total supply, and mintable allowance. It also distinguishes this tool from get_attestation by noting this is the issuer's own tally, so an agent can tell the two apart.
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 description explicitly marks this as the issuer's own KorDA tally and advises verifying supply on-chain via get_attestation.contracts, and it warns that auditor assurance only extends to get_attestation.asOf. This gives clear when-to-use and when-to-alternative guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
KGLD: ask the independent auditor to confirm the reserve report by email. Give ownerEmail (the requester's address): the auditor replies directly to that address from the auditor's own mail — this server is NOT in the reply path, so the reply cannot be fabricated by the issuer. The response returns verificationCode (the auditor writes it in the reply). The requester checks: the sender is the auditor's official domain (look it up independently — this server does not disclose it), code matches, hash/as-of match get_attestation. May take business days; may not be answered. Ask the user for their email before calling; call once per report. / 회계법인이 요청자 메일로 직접 답장. 호출 전 메일 주소 확인.
| Name | Required | Description | Default |
|---|---|---|---|
| ownerEmail | Yes | 회계법인 답장을 받을 요청자 메일 주소 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and delivers: the server is NOT in the reply path so the reply cannot be fabricated by the issuer, the response returns verificationCode, the requester must verify the sender's domain (which the server deliberately does not disclose), and timing is non-deterministic. This is unusually rich behavioral context for a mutation-like call.
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?
Dense but front-loaded: purpose first, then the trust model, then the return value, then caveats and calling instructions. Every sentence carries load, though the mixed English/Korean tail is slightly redundant with the body.
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?
No output schema and no annotations, yet the description still covers the return value (verificationCode), the trust/verification procedure, timing expectations, and pre-call requirements. An agent has everything needed to call it correctly and interpret the result.
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% (the single ownerEmail is documented in the schema), so the baseline is 3. The description goes further by explaining why the field matters — the auditor replies directly to this address, and it is the requester's own mailbox — adding operational meaning beyond the schema's brief Korean gloss.
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 and resource: 'ask the independent auditor to confirm the reserve report by email.' It distinguishes itself from siblings by tying its output to get_attestation ('hash/as-of match get_attestation'), so an agent can place it in the workflow without opening other schemas.
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 invocation guidance: 'Ask the user for their email before calling; call once per report,' plus expectations ('May take business days; may not be answered'). It references get_attestation for cross-checking but does not explicitly state when to prefer this over get_reserve/get_attestation, leaving a small gap.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_attestationget_reserverequest_verificationKGLD gold-token reserve proof: custody vs supply, auditor report hash, human verification by email
KYA backed by a real company: e-CNPJ-signed agent mandates, revocation-checked, signed verdicts
ReserveOracle - 11 stablecoin reserve tools: attestations, composition, MiCA Art.36/37.
No-key MCP: audit/certify MCPs, signed trust history; join Gold Rush Town & build with your LLM.
Add one secure layer between your agents and this server.