Stablecoin reserve attestations as JSON: reserves, composition, attestor, on-chain supply, ratio.
Scored across 2 tools
The two tools have clearly separate roles: one enumerates issuers and registry metadata, the other fetches reserve data for a selected issuer. There is no realistic overlap or risk of selecting the wrong one.
Both names share the stablecoin_ prefix, but only stablecoin_list_issuers follows a verb_noun pattern; stablecoin_reserves is noun-only. The naming is still predictable and readable, with only a minor structural deviation.
Two tools is slightly below the typical 3-15 range, but the server's read-only purpose is narrow and both tools are essential. The count feels reasonable rather than thin.
For the stated domain of reading stablecoin reserve attestations, the pair covers the full workflow: discover issuers and available months, then retrieve attestation data with optional period selection. No obvious lifecycle or query operation is missing.
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 readOnly and idempotent. The description adds useful context by stating it is 'Free' and that it 'lists every issuer in the registry', which clarifies scope and side effects without contradicting the annotations.
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?
Two concise sentences with no redundant wording. The first sentence states the action and output fields, the second gives the usage context.
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 no-parameter listing tool, the description fully covers what it returns and how it should be used in relation to the sibling tool. No critical context 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 tool has zero parameters, so there is no parameter behavior to explain. The description accurately reflects this by not referencing any inputs.
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 'List', the resource 'covered stablecoin issuers', and enumerates the fields returned. It also distinguishes itself from the sibling tool by explicitly saying to call it first to pick a symbol for stablecoin_reserves.
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 instructs when to use this tool: 'Call it first to pick a symbol for stablecoin_reserves.' This clearly routes the agent to this tool before the sibling and provides a concrete purpose.
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?
Beyond the annotations (readOnly, idempotent, openWorld), the description discloses payment behavior ($0.02 per call), the PAYMENT_REQUIRED failure mode without credit, the free sample mode, and the behavioral edge case where issuers without third-party attestation return supply only with confidence 'none'. These traits materially affect invocation and result interpretation.
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 dense but every sentence earns its place: purpose and output fields, usage context, parameter guidance, edge-case behavior, pricing, and sample mode are all covered with no filler. The most important information is front-loaded.
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?
Given the output schema exists, the description does not need to explain return values. It covers enough context for successful invocation: parameter roles, month selection, cost/failure modes, sampling, and the confidence-none case. The description is complete for a tool of this complexity.
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 schema already documents each parameter. The description adds useful semantics by explaining that 'period=YYYY-MM selects an earlier month', that symbol or issuer can be passed, and that sample=true provides a free example response. This adds value beyond the schema without being redundant.
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 opens with a precise statement: it returns the latest parsed reserve attestation for one stablecoin issuer as JSON, naming key fields such as as_of, total reserves, composition, attestor, source_url, supply, and reserve ratio. This clearly identifies the operation and resource, and the data-domain focus distinguishes it from the sibling stablecoin_list_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?
The description explicitly says to use the tool when an agent needs machine-readable backing data instead of the issuer's PDF, and it explains how to select months and sampling. It does not explicitly state when not to use it or direct the agent to an alternative tool, but the usage context is clear enough for selection.
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_reservesReserveOracle - 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.
MiCAOracle — 24 tools for EU MiCA stablecoin compliance: peg, reserves, attestations.
Add one secure layer between your agents and this server.
