Contradiction-verified, freshness-SLA'd signed feed: per-record status + as-of date + receipt.
Scored across 4 tools
Each tool serves a distinct purpose: feed_status retrieves feed-level snapshots, verify_receipt checks receipt integrity, verify_record verifies a single feed record, and verify_subject performs independent subject checks. No functional overlap.
Three tools follow the verb_noun pattern (verify_*), but feed_status is a noun_noun phrase, breaking consistency. All use lowercase with underscores, which is acceptable.
Four tools are well-scoped for a verification server covering feed status, receipt verification, record verification, and subject verification. No unnecessary tools.
The set covers the core verification lifecycle: checking feed status, verifying records and subjects, and validating receipts. Missing a tool for listing feeds or retrieving specific receipts, but not critical.
Return the latest verification snapshot of a minted feed: per-record status + as-of date + stale flags (records past the feed's freshness SLA) + signed receipts. Try slug 'govcon-demo'.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses key behaviors: it returns the latest snapshot, includes stale flags based on freshness SLA, and provides signed receipts. However, with no annotations, it lacks details on error handling, authentication, or how outdated slugs are handled, leaving some behavioral ambiguity.
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 single, well-structured sentence that first states the purpose and output components, then provides a concrete usage example. Every part is essential and there is no redundant information.
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 simple input schema (one required parameter) and no output schema, the description fairly captures what the tool returns. It lists all major output components and includes a usage hint. Minor gaps like missing return format or error cases are acceptable for a straightforward 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 schema has one required parameter (slug) with no description (0% coverage). The description offers an example ('Try slug 'govcon-demo'') which hints at slug being a feed identifier, but does not fully define its format or acceptable values, providing only partial semantic guidance.
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 it returns 'the latest verification snapshot of a minted feed' and lists specific components (per-record status, as-of date, stale flags, signed receipts). This distinguishes it from siblings like verify_receipt, which focus on individual records.
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?
Although the description includes an example slug ('govcon-demo') implying a use case, it does not explicitly state when to use this tool versus the sibling tools (verify_receipt, verify_record, verify_subject). Usage context is implied but not clearly delineated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recompute + verify a verification receipt's hash-chain (proves the verification is unaltered since its as-of date). Pass the receipt id.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It mentions recomputing and verifying a hash-chain, implying mutation and verification, but lacks details on side effects, permissions, or failure modes. Adequate but not thorough.
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 sentences, front-loaded with purpose. Every word adds value with no redundancy.
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 tool's simplicity (single parameter, no output schema), the description covers the core functionality but omits return values, prerequisites, and edge cases. Adequate for a simple tool 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?
Schema coverage is 0%, so the description must compensate. It states 'Pass the receipt id', adding meaning to the 'id' parameter, but no format or constraints are provided, leaving gaps.
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 action (recompute and verify) and the resource (verification receipt's hash-chain), and explains the purpose (proves unaltered since as-of date). It is distinct from sibling tools like verify_record and verify_subject.
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?
No explicit guidance on when to use this tool vs alternatives. The description simply instructs to pass the receipt id, but does not provide context or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Run a contradiction-verified, signed verification on ONE record of a data owner's feed. Attaches a verification STATUS (VERIFIED / CONTRADICTED / EXCLUSION_HIT / UNVERIFIABLE), an AS-OF date, source links, and a tamper-evident hash-chain receipt — by re-checking the record's subject against the live contradiction-engine (SEC 10-K vs USAspending) and, for named entities, the live exclude-feed. A dated evidence statement, never a guarantee.
| Name | Required | Description | Default |
|---|---|---|---|
| feed | No | Feed slug the record belongs to (used for SLA + receipt scoping). | |
| record | Yes | { id, subject:{ticker?, name?}, claim? } |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It discloses the verification process, live checks, attached information (status, as-of date, sources, receipt), and the caveat that it is a dated evidence statement, never a guarantee.
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 relatively concise, packing significant detail into two sentences. It is front-loaded with the primary action and clearly structured, though the first sentence is long and could be broken for readability.
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 tool's complexity (contradiction engine, multiple statuses, hash-chain receipt), the description covers all essential aspects: inputs, process, outputs, and limitations. No output schema exists, so the description adequately replaces it.
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?
Input schema coverage is 100%, so baseline is 3. The description adds context about the verification process and outputs, but does not provide additional semantic meaning for each parameter beyond what the schema already defines.
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 runs a contradiction-verified, signed verification on one record of a data owner's feed, listing specific statuses and outputs. It distinguishes itself from siblings like verify_subject by focusing on a single record.
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 usage for verifying a single record and checking against live engines, but does not explicitly provide when to use this tool versus alternatives like verify_subject or verify_receipt.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
One-off contradiction-verified check of a single subject (ticker and/or named entity) against the live hubs, with an as-of date and signed receipt. Free preview shows status only; paid call returns full detail + receipt.
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | ||
| ticker | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. States free preview returns status, paid returns full detail + receipt, indicating behavioral tiers. But lacks details on side effects, error conditions, or authentication needs.
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 sentences, front-loaded with purpose, followed by valuable additional info on preview vs paid. Every sentence earns its place with no redundancy.
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 no output schema, description explains return values: status for free, full detail + receipt for paid. Covers core behavior but omits specifics like status meaning or error handling. Overall adequate.
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?
Adds meaning beyond schema: explains that 'name' and 'ticker' are for a single subject, and can be used together or separately. This compensates for 0% schema description coverage, making parameter usage clear.
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 clearly states verb ('check'), resource ('subject'), and context ('contradiction-verified', 'live hubs', 'as-of date', 'signed receipt'). Distinguishes from siblings by specifying it's a one-off check for a single subject, while siblings likely handle receipts or records.
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?
Implies usage for initial verification of a single subject, with free vs paid options indicating a threshold. However, no explicit guidance on when to use this tool vs alternatives like verify_receipt or verify_record, nor exclusion conditions.
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.
feed_statusverify_receiptverify_recordverify_subjectBusiness-published entity records with confirmation dates: look up, page feeds, check claims.
Market evidence with receipts: every claim resolves to a real stored record you can fetch back.
Check claims against a fact-store: consistent, contradicts, or unverifiable — with a receipt.
Dated, signed compliance-evidence packs: gov-fact-grounded claims + exclusion screens + trap-facts.
Add one secure layer between your agents and this server.