Signed citation-integrity reports + retraction-checked evidence packs, paid per call via x402/USDC.
Scored across 6 tools
The two workflows are clearly separated: citation_report family verifies bibliographies, while evidence_pack finds scholarly candidates. However, citation_report vs citation_report_large and evidence_pack vs evidence_pack_preview are close enough that an agent must carefully read limits and payment terms to avoid selecting the wrong variant.
All tool names follow a consistent snake_case pattern built on a domain noun plus modifier: citation_report, citation_report_large, citation_report_preview, citation_report_receipt, evidence_pack, evidence_pack_preview. There are no mixed conventions or irregular naming styles.
Six tools is well-scoped for this domain: two paid core operations, two free previews, one large-capacity tier, and one receipt-lookup tool. The count is neither bloated nor too thin for the server's stated purpose.
The citation-report lifecycle is well covered: preview, paid verification, large batches, and receipt re-fetching. The main gap is that paid evidence_pack results have no equivalent receipt or re-fetch tool, leaving that workflow slightly less complete.
Verify a bibliography. For every reference: exists, resolves, retracted/corrected/flagged, title/author/year match against the registered record, and a rule-derived fabrication risk — as a signed (Ed25519, RFC 8785 canonical JSON), byte-reproducible JSON report. Input: structured references or BibTeX. No LLM; every claim carries its source and retrieval time. Up to 50 references. Paid: $1.00 USDC per successful call via x402 (eip155:8453). An unpaid call returns the payment requirements (isError). Results carry settled / transaction / network / payer plus the signed report.
| Name | Required | Description | Default |
|---|---|---|---|
| bibtex | No | A BibTeX bibliography (entry key → reference id). | |
| options | No | ||
| references | No | Structured references. Exactly one of references / bibtex. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden and does so thoroughly: deterministic, grounded and signed output ('signed (Ed25519, RFC 8785 canonical JSON), byte-reproducible', 'No LLM; every claim carries its source and retrieval time'), the payment gate with its exact failure behavior ('unpaid call returns the payment requirements (isError)'), and the full output envelope ('settled / transaction / network / payer plus the signed report'). This is substantially more behavioral disclosure than the schema or annotations provide.
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 purpose arrives in the first sentence, and each subsequent clause earns its place: the checks, the input format, the deterministic/signed property, the reference cap, and the payment flow. The detail density is high but justified by the unusual combination of payment, signing, and retraction checks; only the packed middle segment (proof/signing details and payment) could be restructured slightly for scanability.
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 complex tool with no output schema and no annotations, the description is nearly complete: it covers input constraints, behavior, limits, failure mode, cost, and return value composition. The remaining gaps are minor — the behavioral effect of strict_authors / include_unpaywall is not described, and handling of reference items that fail to resolve is not covered — but they are evident enough to keep this out of perfect.
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 67%, placing this in mid-range territory where description must still compensate for gaps. The description adds the effective 50-reference cap (the schema allows up to 200) and states that input is either structured references or BibTeX. However, the only nested object, 'options' — with strict_authors and include_unpaywall — receives zero semantic meaning in the description, so a meaningful portion of the input surface is left for the agent to guess.
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 specific verb and resource — 'Verify a bibliography' — then lists a precise checklist of checks (exists, resolves, retracted/corrected/flagged, title/author/year match, fabrication risk). It differentiates itself from siblings by explicit constraints: 'standard tier', 'Up to 50 references' (setting it apart from citation_report_large), the signed-report delivery (vs. citation_report_receipt), and the paid gate (vs. citation_report_preview).
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 provides clear context — paid standard tier, up to 50 references, full verification with signing — which implies when this tool is appropriate. However, it never names the alternatives or states explicit conditions like 'use citation_report_preview to test without paying' or 'use citation_report_large beyond 50 references'. An agent must infer the routing from the tier/limit details rather than read it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Verify a bibliography. For every reference: exists, resolves, retracted/corrected/flagged, title/author/year match against the registered record, and a rule-derived fabrication risk — as a signed (Ed25519, RFC 8785 canonical JSON), byte-reproducible JSON report. Input: structured references or BibTeX. No LLM; every claim carries its source and retrieval time. Up to 75 references. Paid: $3.00 USDC per successful call via x402 (eip155:8453). An unpaid call returns the payment requirements (isError). Results carry settled / transaction / network / payer plus the signed report. NOTE: $3.00 is above the @x402/core client's default spend cap (maxAmountPerPayment $1.00); raise it (client.setSpendControls) before calling, or the client refuses without sending anything.
| Name | Required | Description | Default |
|---|---|---|---|
| bibtex | No | A BibTeX bibliography (entry key → reference id). | |
| options | No | ||
| references | No | Structured references. Exactly one of references / bibtex. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are absent, so the description carries the full burden and it handles it thoroughly: it discloses the Ed25519/RFC-8785 signed byte-reproducible JSON, no-LLM provenance, the $3.00 per-call payment, the unpaid isError response, the returned payment-settled fields, and the client-side spend-cap failure mode. This goes well beyond typical descriptions.
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 text is dense but earns every phrase: checks, signing format, input kinds, no-LLM guarantee, pricing, error behavior, and the spend-cap workaround are each actionable. Nothing is filler, and the most time-critical warning about the client default cap is placed where it can prevent a failed call.
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 tool with no output schema, the description conveys nearly everything needed to call it correctly: the checks performed, input constraints, payment flow, failure modes, and the exact client configuration to change. The main completeness gaps are the undocumented options object and the unresolved 75-versus-200 references discrepancy, so it is very strong but not fully complete.
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 description only restates that input is structured references or BibTeX, which the schema already conveys (67% coverage). It does not explain the options object or the boolean options strict_authors and include_unpaywall, and it says "up to 75 references" while the schema's maxItems is 200, leaving an unexplained discrepancy that suppresses additional semantic value.
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: "Verify a bibliography" and enumerates concrete checks: existence, resolution, retraction, title/author/year match, and fabrication risk. The "large tier" plus paid/75-reference bound distinguishes it from the sibling citation_report family even without opening the schema.
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 clear context: input can be structured references or BibTeX, supports up to 75 references, and requires a paid x402 call, including a specific spend-cap warning that the client refuses to send otherwise. It does not explicitly name alternatives or explain when to choose this over citation_report_preview or citation_report, so it stops short of explicit when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Free preview. Verify a bibliography. For every reference: exists, resolves, retracted/corrected/flagged, title/author/year match against the registered record, and a rule-derived fabrication risk — as a signed (Ed25519, RFC 8785 canonical JSON), byte-reproducible JSON report. Input: structured references or BibTeX. No LLM; every claim carries its source and retrieval time. Checks only the first 3 references; unsigned; no payment.
| Name | Required | Description | Default |
|---|---|---|---|
| bibtex | No | A BibTeX bibliography (entry key → reference id). | |
| options | No | ||
| references | No | Structured references. Exactly one of references / bibtex. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses several behavioral traits: no LLM involvement, every claim carries source and retrieval time, byte-reproducible JSON, and a 3-reference limit. However, it contradicts itself by describing the output as 'signed (Ed25519...)' and then declaring it 'unsigned'; it also says 'For every reference' then limits to the first 3. These inconsistencies undermine trust in the description's accuracy.
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 a dense single block of semicolon-separated clauses rather than a well-structured, front-loaded summary. It contains valuable information but is hard to parse quickly and includes redundant or contradictory statements. A bulleted list or clearer separation of caveats would improve 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?
There is no output schema, so the description's mention of the JSON report contents and per-reference checks is helpful. It also covers input types and the preview limitation. Yet the signed/unsigned contradiction and the lack of explanation for the options parameter leave meaningful gaps for an agent deciding how to invoke the tool correctly.
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 67%, so the schema already documents bibtex and references well. The description adds that input can be structured references or BibTeX, which matches those parameters, but it provides no additional detail about the 'options' object or how the booleans behave. This is adequate but not compensating beyond the schema.
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 clearly states the tool verifies a bibliography and enumerates the checks performed for each reference (existence, resolution, retraction/correction, metadata match, fabrication risk). It distinguishes itself as a free preview limited to 3 references, which separates it from the sibling citation_report tools. However, the output description is confusing because it first says 'signed' then later says 'unsigned', muddying what exact artifact is produced.
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 conveys when this tool is appropriate: it is a free preview, checks only the first 3 references, is unsigned, and requires no payment. This implies a limited trial use case and distinguishes it from paid/full-report siblings. It does not explicitly name alternatives like citation_report, but the preview limitation is an adequate usage signal.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Re-fetch a paid report you already bought, by its request_id, within the cache TTL. Free; no payment; the same signed report (request_id re-attached, unsigned, as on the paid result). Over the hosted endpoint GET /v1/citation-report/receipts/ serves the same bytes; over a local stdio run only that process can. Not found after the TTL, for previews, or for reports served by another process.
| Name | Required | Description | Default |
|---|---|---|---|
| request_id | Yes | The request_id from a paid citation_report / citation_report_large result. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are absent, so the description must carry all behavioral disclosure. It fully does so: it states the operation is free ('Free; no payment'), clarifies the output is an unsigned copy of the same report ('the same signed report ... unsigned'), covers transport behavior for hosted vs. local stdio, and lists all negative conditions when lookup fails ('Not found after the TTL, for previews, or for reports served by another process'). This is comprehensive and goes beyond what annotations usually provide.
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 three sentences that are dense but front‐loaded: the core purpose and TTL frame come first, followed by transport behavior, then disqualifiers. Each sentence adds a distinct piece of information. The middle parenthetical '(request_id re-attached, unsigned, as on the paid result)' is slightly convoluted but not wasted. It is concise relative to the amount of behavior it conveys.
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?
The tool has one parameter, no output schema, and no annotations. The description covers the main needs for correct invocation: what to provide, what you get back ('same bytes'), and when it fails. It does not mention response format or error messages, but for a re-fetch of an existing report, the output is already defined by the original report. The only plausible completeness gap is the absence of explicit note about whether the request_id must be within a signed session, but the TTL removal is already mentioned.
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 description already documents that request_id is 'the request_id from a paid citation_report / citation_report_large result' (100% coverage). The description adds the behavioral constraint 'within the cache TTL' and the requirement 'bought' that ties into the schema context. It does not re-explain the regex or format, which the schema covers. The extra semantics (recency and paid status) are useful and meet the baseline of 3 and exceed it slightly.
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?
Description opens with 'Re-fetch a paid report you already bought, by its request_id', which is a specific verb ('re-fetch'), resource ('a paid report'), and required scope ('you already bought'). It also distinguishes itself from siblings by the explicit exclusion 'for previews' and the paid/free contrast, so an agent can differentiate it from citation_report, citation_report_preview, and citation_report_large without opening a schema.
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?
Usage is clearly scoped to already-paid reports: 'Re-fetch a paid report you already bought.' The description also states when the tool is not to be used (beyond TTL, for previews, for reports served by another process). It does not name sibling tools by name (e.g., 'citation_report_preview') but the term 'previews' and the context of local stdio capability cover the alternatives. It could have explicitly said 'instead use ...' to earn a 5, but the guidance is otherwise explicit and accurate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find 3-10 scholarly candidates for a question or topic. Returns DOI/OpenAlex IDs, authors, year, venue, source URLs, citation context, open-access location, and known retraction/correction warnings. JSON only. Does not claim that a paper proves a statement. Paid: $0.03 USDC per successful call via x402 (eip155:8453). An unpaid call returns the payment requirements (isError). Results carry settled / transaction / network / payer.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Papers to return (3-10, default 5). | |
| query | Yes | Question, claim, or research topic. | |
| fields | No | Optional response minimization. | |
| to_year | No | ||
| from_year | No | ||
| open_access_only | No | ||
| exclude_known_retracted | No | Default keeps retracted records but marks them; true filters them. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description carries the full behavioral burden since no annotations are supplied. It clearly discloses the paid fee, payment network, unpaid-call error behavior, JSON-only responses, and the epistemic limitation about not proving claims. It does not cover rate limits, retries, or authentication details, so it is not a perfect 5.
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 main action and output contents, and quickly follows with payment and failure behavior. Every sentence is relevant and none of the text is 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 paid tool with no output schema and no annotations, the description covers the main invocation realities: response fields, payment side effects, error response, and the tool's knowledge claims. It could be slightly stronger by connecting parameters like from_year, to_year, and open_access_only to their possible effect on results.
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 only 57% and the description adds little parameter-level meaning beyond the query concept and the 3-10 limit. The year filters, open_access_only, and fields parameters are not explained in the description and mainly rely on schema inference.
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: find 3-10 scholarly candidates for a question or topic, and it enumerates the returned scholarly fields. It is clear but does not explicitly contrast evidence_pack with the sibling tools such as evidence_pack_preview or citation_report.
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 implies the main use case: retrieve scholarly candidate papers and evidence metadata for a topic or question. It also notes an important limitation, that it does not claim a paper proves a statement, but it does not explicitly say when to choose this tool over the preview or citation-report siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Free preview. Find 3-10 scholarly candidates for a question or topic. Returns DOI/OpenAlex IDs, authors, year, venue, source URLs, citation context, open-access location, and known retraction/correction warnings. JSON only. Does not claim that a paper proves a statement. Returns at most 3 papers; no payment.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Question, claim, or research topic. | |
| fields | No | Optional response minimization. | |
| to_year | No | ||
| from_year | No | ||
| open_access_only | No | ||
| exclude_known_retracted | No | Default keeps retracted records but marks them; true filters them. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full behavioral burden and mostly succeeds: it discloses JSON-only output, a hard cap of 3 papers, no payment, and the important caveat that it does not claim a paper proves a statement. It doesn't cover rate limits or failure behavior, but the key behavioral traits are transparent.
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 and front-loaded, but it contains a direct contradiction between '3-10 scholarly candidates' and 'Returns at most 3 papers.' It also repeats the free/no-payment idea twice, which slightly reduces the clarity and efficiency of the text.
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 six-parameter tool with no output schema, the description covers the main return fields and an important epistemic caveat, which is useful. However, it omits parameter semantics and leaves the candidate-count inconsistency unresolved, so an agent may misjudge result limits and available filters.
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 only 50%, and the description adds little parameter meaning beyond the schema. It does not explain to_year, from_year, or open_access_only, nor does it clarify defaults or interactions with fields. The query parameter is the only one implicitly supported by the description.
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 uses a specific verb ('Find') and identifies the resource ('scholarly candidates'), and it lists the key returned identifiers and metadata. The free-preview framing also distinguishes it from the paid evidence_pack sibling. However, the result count is internally inconsistent ('3-10 scholarly candidates' vs 'Returns at most 3 papers'), which blurs the scope.
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 'Free preview' and 'no payment' phrasing implies this is a limited no-cost alternative to the full evidence_pack tool, but it never explicitly states when to choose this tool over evidence_pack or the citation_report siblings. Usage context is present but only by implication.
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.
citation_reportcitation_report_largecitation_report_previewcitation_report_receiptevidence_packevidence_pack_previewVerify official facts with Bitcoin-anchored proof. 180+ signals, x402 pay-per-call.
Compact, citation-verifiable public web context for AI agents, paid per use with x402.
Pay-per-call government data over x402: provenance chains, Ed25519 attestations, no API keys.
Bi-temporal memory-as-a-service and paid agent labor. Pay-per-call USDC via x402; signed receipts.
