Stablecoin reserve attestations as JSON: reserves, composition, attestor, on-chain supply, ratio.
Scored across 2 tools
The two tools have clearly distinct roles: one enumerates issuers, the other retrieves reserve data for a single symbol/issuer. The list tool's description explicitly instructs calling it first to pick a symbol, eliminating selection ambiguity.
Both names share a predictable 'stablecoin_' prefix and snake_case style. The second name (stablecoin_reserves) drops the verb_noun convention of the first (stablecoin_list_issuers), a minor deviation.
Two tools is on the thin side, though the domain (a stablecoin issuer registry plus per-issuer reserve data) is genuinely narrow. It covers the core list-then-detail flow but leaves little room for richer querying.
The surface covers enumeration plus detailed lookup with period selection, on-chain supply, reserve ratio, sample responses, and payment handling. Minor gaps remain, such as cross-issuer comparison or bulk retrieval, but core workflows are covered.
Free. Lists every issuer in the registry with symbol, issuer, attestation type, attestor, cadence, source_url and which months are parsed. Call it first to pick a symbol for stablecoin_reserves.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| count | Yes | |
| notice | Yes | |
| issuers | Yes | |
| price_usd_per_reserves_call | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely new traits the annotations cannot express: that the call is free and that it returns 'every' issuer (i.e., no filtering or pagination caveat). It stops short of noting auth requirements or response size, but the added cost and completeness signals are real value.
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?
Three compact sentences with the highest-value fact ('Free.') front-loaded, then payload, then the routing instruction. No sentence is filler and the ordering matches how an agent would use it.
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 an output schema present, the description need not explain return structure, and it correctly focuses on scope and sequencing instead. For a zero-parameter registry listing, everything needed to call it correctly is present.
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 the baseline is 4 per the rubric; there are no argument semantics that need explaining. The description cannot add parameter meaning because none exist.
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 (lists every issuer in the registry) and enumerates the exact fields returned, so an agent knows precisely what it gets. It is clearly distinguishable from the sibling stablecoin_reserves, which is a data-fetch rather than a registry enumeration.
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?
Explicitly prescribes ordering: 'Call it first to pick a symbol for stablecoin_reserves.' That names the alternative tool and the condition under which this one precedes it, leaving nothing to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Latest parsed reserve attestation for one stablecoin issuer as JSON: as_of date, total reserves, composition by asset category, attestor, source_url, current on-chain supply (DefiLlama) and the reserve ratio. Use it when an agent needs machine-readable backing data instead of reading the issuer's PDF. Pass symbol (USDC, USDT, ...) or issuer; period=YYYY-MM selects an earlier month. Issuers without a third-party attestation return supply only with confidence 'none'. Paid: $0.02 per call; without credit you get a PAYMENT_REQUIRED result. Set sample=true for a free example response.
| Name | Required | Description | Default |
|---|---|---|---|
| issuer | No | Issuer name or registry id when the symbol is unknown, e.g. "circle" or "paxos" | |
| period | No | Report month as YYYY-MM. Default: the newest parsed month. See history_available. | |
| sample | No | Set true to return an example response at no charge (sample mode). Default false. | |
| symbol | No | Token symbol, case-insensitive: USDC, USDT, PYUSD, RLUSD, ... (see stablecoin_list_issuers) |
| Name | Required | Description |
|---|---|---|
| peg | Yes | |
| name | Yes | |
| as_of | Yes | |
| checks | Yes | |
| issuer | Yes | |
| notice | Yes | |
| period | Yes | |
| sample | Yes | |
| symbol | Yes | |
| backing | Yes | |
| cadence | Yes | |
| sources | Yes | |
| attestor | Yes | |
| currency | Yes | |
| issued_on | Yes | |
| confidence | Yes | |
| report_url | Yes | |
| source_url | Yes | |
| composition | Yes | |
| reserve_ratio | Yes | |
| onchain_supply | Yes | |
| attestation_type | Yes | |
| history_available | Yes | |
| total_reserves_usd | Yes | |
| tokens_in_circulation_reported | Yes | |
| reserve_ratio_vs_onchain_supply | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With annotations present the bar is lower, and the description adds real operational context the annotations do not carry: per-call cost ($0.02), the PAYMENT_REQUIRED failure mode when credit is absent, free sample mode, and the 'confidence none, supply only' behavior for issuers lacking third-party attestation. readOnlyHint=false and idempotentHint=false are consistent with a per-call billed fetch, though destructiveHint=true is left unexplained for a pure data-retrieval 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?
Front-loaded with purpose and return shape, then usage, then billing and sample mode — a sensible ordering. It is a single dense paragraph with some restatement of schema details (period, sample), so it is efficient but not maximally tight.
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?
An output schema exists, so return-field enumeration is optional and the description spends its words well on payment, sample mode, period default and the unattested-issuer case. It leaves minor unresolved points: the semantics of destructiveHint/non-idempotency and the behavior when neither symbol nor issuer is passed.
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 100%, so issuer, period, sample and symbol are already documented in the schema; the description largely restates them (symbol or issuer, period=YYYY-MM selects an earlier month, sample=true for a free example). It adds no format or precedence rules beyond the schema, and notably does not say what happens when no parameter is supplied even though none are required. Baseline 3 is appropriate.
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+resource: 'Latest parsed reserve attestation for one stablecoin issuer as JSON', then enumerates the payload (as_of, total reserves, composition, attestor, source_url, on-chain supply, reserve ratio). It is unmistakable against the sibling stablecoin_list_issuers, which only lists issuers.
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 a clear selection condition: 'Use it when an agent needs machine-readable backing data instead of reading the issuer's PDF', plus how to reach an earlier month via period=YYYY-MM and how to get a free trial via sample=true. It stops short of an explicit when-not or naming the sibling as the alternative, so it is contextual rather than exhaustive.
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.
stablecoin_list_issuersstablecoin_reservesAttested risk scores for stablecoins, DeFi protocols and wallets, with receipts.
ReserveOracle - 11 stablecoin reserve tools: attestations, composition, MiCA Art.36/37.
Signed verification attestations for agent decisions: business, price, freshness, claim checks.
Uptime and price-honesty oracle for x402: trust status, attestations, USDC history.
Add one secure layer between your agents and this server.
