Timestamped public URL observations with SHA-256 fingerprints, paid in USDC on Base via x402.
Scored across 4 tools
Tools have distinct roles: info, observation, proof verification, and combined verification. The main overlap is verify_url, which subsumes observe_url and verify_proof by combining both, so an agent might occasionally choose observe_url when verify_url was intended. Descriptions clearly explain the difference, keeping ambiguity low.
Most names follow a verb_noun pattern (observe_url, verify_proof, verify_url) in consistent snake_case. The exception is freshproof_info, which is server-prefixed rather than verb-led, a minor deviation from an otherwise predictable scheme.
Four tools are well-scoped for a focused observation and proof-verification service. Each tool has a clear, non-redundant purpose: info, observe, verify existing proof, and combined observe-and-verify. No tool feels extraneous or missing at this granularity.
The surface covers the full lifecycle: learn about the service, buy an observation, verify an existing proof, and perform combined observation plus verification. Free and paid options are both represented, with no obvious dead ends for the stated domain.
Describe FreshProof, its observation semantics, current MCP price and payment network. This tool is free.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that the tool is free, which is a useful behavioral trait. However, it does not describe the return format, potential delays, or whether it performs any side effects (though as an info tool, side effects are unlikely). The description is adequate but not rich in behavioral detail.
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 with zero waste. The primary purpose is front-loaded, and the note about being free is appended clearly. Every word earns its place.
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 zero-parameter informational tool, the description is complete: it tells the agent exactly what information will be provided. It doesn't specify the response format (e.g., plain text vs. JSON), but that's a minor omission given the tool's simplicity and the absence of an output schema.
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, and the schema shows no properties. Per the rubric, a 0-param tool gets a baseline of 4. The description adds no parameter-specific meaning because there are no parameters to explain. The baseline score applies.
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's purpose: to describe FreshProof, its observation semantics, pricing, and payment network. It uses a specific verb ('describe') and names the exact subjects, making it unambiguous. It also distinguishes itself from the sibling tool 'observe_url' by focusing on informational content rather than observation actions.
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 (call this when you need info about FreshProof), but it does not explicitly state when to use it vs. the sibling 'observe_url' or mention any exclusions. There is no direct guidance on when not to use it, though the contrast with the sibling is implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Buy a timestamped FreshProof observation of a public HTTP/HTTPS URL. Returns final URL, observation timestamp, age, HTTP status, SHA-256 body hash, body size, ETag, Last-Modified, fetch duration, and whether the observation came from shared cache or a fresh public-network request. Set max_age=0 when a new public-network request is required. The response body itself is not returned.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Public HTTP or HTTPS URL to observe | |
| max_age | No | Maximum acceptable observation age in seconds. Defaults to 300. Set to 0 to force a fresh public-network request. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already signal read-only/non-destructive behavior; the description adds important behavior beyond that: shared-cache vs fresh-fetch semantics, the effect of max_age=0, the fact that the response body is never returned, and the full list of returned fields. This gives an agent an accurate model of what happens at call time.
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 core purpose is front-loaded in the first sentence, and the remaining sentences efficiently convey freshness control and the key exclusion ('response body itself is not returned'). No filler or repetition.
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?
Even without an output schema, the description enumerates all relevant return fields and explicitly states the body is not returned. For a two-parameter tool with safe annotations, this is complete enough for an agent to invoke it correctly without further inference.
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?
Both parameters are fully documented in the schema (100% coverage), so the description does not need to compensate. It reinforces the max_age=0 behavior already in the schema and adds the cache-vs-fresh nuance, but the incremental meaning over the schema is modest.
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: 'Buy a timestamped FreshProof observation of a public HTTP/HTTPS URL', immediately distinguishing it from the only sibling (freshproof_info). It also enumerates exactly what is returned, so there is no ambiguity about what the tool does.
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 gives clear operational guidance: use max_age=0 when a fresh public-network request is required, and otherwise an older cached observation is acceptable. It does not explicitly contrast with freshproof_info or state when not to use this tool, so it stops short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Verify an existing FreshProof Proof Receipt without making a new network request. This free tool checks deterministic receipt integrity and optionally evaluates trust policy rules. Use it when you already have a proof_id from observe_url or verify_url and want to re-check evidence without paying for another observation. The result includes valid, decision (PASS, FAIL, or UNKNOWN), per-rule checks, and the stored receipt.
| Name | Required | Description | Default |
|---|---|---|---|
| policy | No | Optional declarative trust policy. All supplied rules must pass for decision PASS; any failed rule yields FAIL. UNKNOWN is reserved for cases where FreshProof cannot make a reliable policy decision. | |
| proof_id | Yes | FreshProof proof identifier returned by observe_url or verify_url. |
| Name | Required | Description |
|---|---|---|
| valid | Yes | True when the stored receipt passes deterministic integrity verification. |
| checks | Yes | |
| receipt | Yes | |
| decision | Yes | Overall policy decision. PASS means every supplied rule passed; FAIL means at least one supplied rule failed; UNKNOWN means a reliable decision could not be made. |
| proof_id | Yes | FreshProof proof identifier returned by observe_url or verify_url. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds value beyond that: no network request, free of cost, deterministic receipt integrity check, and optional trust-policy evaluation. It does not disclose side effects or failure modes beyond the decision semantics, which are partly also in the output schema.
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 sentences, front-loaded with the core action and constraint, each earning its place: purpose, use condition, and return shape. No filler or repetition of the name.
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 full annotation coverage, 100% schema description coverage, and an output schema present, the description need not restate return values. It supplies the missing behavioral context (no network call, free, deterministic) and is complete for correct invocation.
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% and the policy object properties are fully documented in the schema, so the baseline is 3. The description only signals that policy evaluation is optional, adding little meaning beyond what the schema already provides for proof_id and each rule.
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 (verify) and resource (FreshProof Proof Receipt) plus the key differentiator: it makes no new network request. This clearly separates it from observe_url and verify_url, which produce or refresh proofs, so an agent can route correctly without opening 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 an explicit precondition ('when you already have a proof_id from observe_url or verify_url') and the motivation ('without paying for another observation'). It lacks an explicit when-not clause or an enumerated alternative tool, but the condition that selects this tool over its siblings is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Verify what is observable at a public URL before an agent trusts, pays, or acts. This paid tool combines observe_url and verify_proof in one call: it buys an observation, creates or returns a Proof Receipt, and evaluates the supplied trust policy. Set max_age=0 when current public-network evidence is required. The result contains both observation evidence and verification with decision PASS, FAIL, or UNKNOWN.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Public HTTP or HTTPS URL to observe and verify. | |
| policy | Yes | Declarative trust policy evaluated against the resulting Proof Receipt. | |
| max_age | No | Maximum acceptable observation age in seconds. Defaults to 300. Set to 0 to require a fresh public-network request before policy evaluation. |
| Name | Required | Description |
|---|---|---|
| observation | Yes | |
| verification | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Goes well beyond the annotations by disclosing that the call is paid, that it buys an observation and creates or returns a Proof Receipt, and that the decision space is PASS/FAIL/UNKNOWN. The remaining gap is that the advertised purchase/receipt-creation side effect is not reconciled with readOnlyHint=true, leaving a small ambiguity about exactly what state the call mutates.
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?
Four sentences, purpose front-loaded, then mechanism, then a parameter tip, then the result shape. Tight overall, though the max_age=0 guidance partially duplicates the schema description, which is the one sentence that does not fully earn its place.
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, open-world, non-idempotent tool with a nested policy object, the description covers cost, mechanism, freshness semantics, and decision vocabulary; an output schema exists so return shape needs no further detail. It does not mention authorization or pricing model, but nothing essential for correct invocation 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?
Schema coverage is 100% and the schema already documents url, policy, and every policy sub-rule in detail, including the max_age default of 300 and the meaning of max_age=0. The description largely restates this ('evaluates the supplied trust policy', 'Set max_age=0'), so it adds little meaning beyond the structured fields.
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 ('Verify what is observable at a public URL') and immediately frames the scope. It explicitly positions itself against siblings by naming observe_url and verify_proof and describing the combination ('combines observe_url and verify_proof in one call'), so an agent can distinguish it 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?
Gives a clear operating context ('before an agent trusts, pays, or acts') and one concrete condition ('Set max_age=0 when current public-network evidence is required'). The implication that this replaces calling observe_url and verify_proof separately is strong but not stated as an explicit when-to-use rule or exclusion, so it falls short of a 5.
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.
verify_proof10 fields changedInput schema / properties / policy / descriptionAdded value: +"Optional declarative trust policy. All supplied rules must pass for decision PASS; any failed rule yields FAIL. UNKNOWN is reserved for cases where FreshProof cannot make a reliable policy decision."Input schema / properties / policy / properties / changed_since_content_hash / descriptionAdded value: +"Prior SHA-256 response-body fingerprint. Passes when the current proof has a different content hash."Input schema / properties / policy / properties / content_hash_equals / descriptionAdded value: +"Expected SHA-256 response-body fingerprint, including the sha256: prefix. Passes only on exact equality."Input schema / properties / policy / properties / final_host_equals / descriptionAdded value: +"Expected lowercase hostname after redirects, for example example.com. Provide a hostname, not a full URL."Input schema / properties / policy / properties / max_age_seconds / descriptionAdded value: +"Maximum allowed age of the stored observation in seconds at verification time."Input schema / properties / policy / properties / original_host_equals / descriptionAdded value: +"Expected lowercase hostname from the originally requested URL. Provide a hostname, not a full URL."Input schema / properties / policy / properties / require_same_origin_redirect / descriptionAdded value: +"When true, fails if the final URL origin differs from the original URL origin after redirects."Input schema / properties / policy / properties / status_in / descriptionAdded value: +"Allowed HTTP status codes. The rule passes when the observed status is in this list."Input schema / properties / proof_id / descriptionPrevious value: -"FreshProof proof identifier returned by observe_url"New value: +"FreshProof proof identifier returned by observe_url or verify_url."Output schema / (root)Previous value: -nullNew value: +{
+ "$schema": "http://json-schema.org/draft-07/schema#",
+ "additionalProperties": false,
+ "properties": {
+ "checks": {
+ "items": {
+ "additionalProperties": false,
+ "properties": {
+ "actual": {
+ "description": "Observed value used by the rule."
+ },
+ "expected": {
+ "description": "Expected value or condition used by the rule."
+ },
+ "pass": {
+ "description": "Whether this individual rule passed.",
+ "type": "boolean"
+ },
+ "rule": {
+ "description": "Policy rule that was evaluated.",
+ "type": "string"
+ }
+ },
+ "required": [
+ "rule",
+ "pass",
+ "actual",
+ "expected"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "decision": {
+ "description": "Overall policy decision. PASS means every supplied rule passed; FAIL means at least one supplied rule failed; UNKNOWN means a reliable decision could not be made.",
+ "enum": [
+ "PASS",
+ "FAIL",
+ "UNKNOWN"
+ ],
+ "type": "string"
+ },
+ "proof_id": {
+ "description": "FreshProof proof identifier returned by observe_url or verify_url.",
+ "pattern": "^fp1_[a-f0-9]{64}$",
+ "type": "string"
+ },
+ "receipt": {
+ "additionalProperties": false,
+ "properties": {
+ "payload": {
+ "additionalProperties": false,
+ "properties": {
+ "content_hash": {
+ "pattern": "^sha256:[a-f0-9]{64}$",
+ "type": "string"
+ },
+ "content_length": {
+ "maximum": 9007199254740991,
+ "minimum": 0,
+ "type": "integer"
+ },
+ "etag": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "fetch_duration_ms": {
+ "maximum": 9007199254740991,
+ "minimum": 0,
+ "type": "integer"
+ },
+ "final_url": {
+ "format": "uri",
+ "type": "string"
+ },
+ "last_modified": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "method": {
+ "const": "GET",
+ "type": "string"
+ },
+ "normalized_url": {
+ "format": "uri",
+ "type": "string"
+ },
+ "observation_id": {
+ "type": "string"
+ },
+ "observed_at": {
+ "description": "ISO-8601 timestamp of the observation.",
+ "type": "string"
+ },
+ "original_url": {
+ "format": "uri",
+ "type": "string"
+ },
+ "status": {
+ "maximum": 599,
+ "minimum": 100,
+ "type": "integer"
+ },
+ "version": {
+ "const": "freshproof-receipt-v1",
+ "type": "string"
+ }
+ },
+ "required": [
+ "version",
+ "observation_id",
+ "normalized_url",
+ "original_url",
+ "final_url",
+ "observed_at",
+ "method",
+ "status",
+ "content_hash",
+ "content_length",
+ "etag",
+ "last_modified",
+ "fetch_duration_ms"
+ ],
+ "type": "object"
+ },
+ "proof_id": {
+ "description": "FreshProof proof identifier returned by observe_url or verify_url.",
+ "pattern": "^fp1_[a-f0-9]{64}$",
+ "type": "string"
+ },
+ "receipt_hash": {
+ "description": "SHA-256 content address of the canonical Proof Receipt payload.",
+ "pattern": "^sha256:[a-f0-9]{64}$",
+ "type": "string"
+ }
+ },
+ "required": [
+ "proof_id",
+ "receipt_hash",
+ "payload"
+ ],
+ "type": "object"
+ },
+ "valid": {
+ "description": "True when the stored receipt passes deterministic integrity verification.",
+ "type": "boolean"
+ }
+ },
+ "required": [
+ "proof_id",
+ "valid",
+ "decision",
+ "checks",
+ "receipt"
+ ],
+ "type": "object"
+}verify_url11 fields changedInput schema / properties / max_age / descriptionAdded value: +"Maximum acceptable observation age in seconds. Defaults to 300. Set to 0 to require a fresh public-network request before policy evaluation."Input schema / properties / policy / descriptionPrevious value: -"Declarative policy evaluated against the resulting proof"New value: +"Declarative trust policy evaluated against the resulting Proof Receipt."Input schema / properties / policy / properties / changed_since_content_hash / descriptionAdded value: +"Prior SHA-256 response-body fingerprint. Passes when the current proof has a different content hash."Input schema / properties / policy / properties / content_hash_equals / descriptionAdded value: +"Expected SHA-256 response-body fingerprint, including the sha256: prefix. Passes only on exact equality."Input schema / properties / policy / properties / final_host_equals / descriptionAdded value: +"Expected lowercase hostname after redirects, for example example.com. Provide a hostname, not a full URL."Input schema / properties / policy / properties / max_age_seconds / descriptionAdded value: +"Maximum allowed age of the stored observation in seconds at verification time."Input schema / properties / policy / properties / original_host_equals / descriptionAdded value: +"Expected lowercase hostname from the originally requested URL. Provide a hostname, not a full URL."Input schema / properties / policy / properties / require_same_origin_redirect / descriptionAdded value: +"When true, fails if the final URL origin differs from the original URL origin after redirects."Input schema / properties / policy / properties / status_in / descriptionAdded value: +"Allowed HTTP status codes. The rule passes when the observed status is in this list."Input schema / properties / url / descriptionPrevious value: -"Public HTTP or HTTPS URL to observe and verify"New value: +"Public HTTP or HTTPS URL to observe and verify."Output schema / (root)Previous value: -nullNew value: +{
+ "$schema": "http://json-schema.org/draft-07/schema#",
+ "additionalProperties": false,
+ "properties": {
+ "observation": {
+ "additionalProperties": false,
+ "properties": {
+ "age_seconds": {
+ "maximum": 9007199254740991,
+ "minimum": 0,
+ "type": "integer"
+ },
+ "content_hash": {
+ "pattern": "^sha256:[a-f0-9]{64}$",
+ "type": "string"
+ },
+ "content_length": {
+ "maximum": 9007199254740991,
+ "minimum": 0,
+ "type": "integer"
+ },
+ "etag": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "fetch_duration_ms": {
+ "maximum": 9007199254740991,
+ "minimum": 0,
+ "type": "integer"
+ },
+ "final_url": {
+ "format": "uri",
+ "type": "string"
+ },
+ "last_modified": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "observed_at": {
+ "description": "ISO-8601 timestamp of the observation.",
+ "type": "string"
+ },
+ "proof_id": {
+ "description": "FreshProof proof identifier returned by observe_url or verify_url.",
+ "pattern": "^fp1_[a-f0-9]{64}$",
+ "type": "string"
+ },
+ "receipt_hash": {
+ "pattern": "^sha256:[a-f0-9]{64}$",
+ "type": "string"
+ },
+ "source": {
+ "description": "fresh_fetch means FreshProof made a new public-network request; shared_cache means a stored observation satisfied max_age.",
+ "enum": [
+ "shared_cache",
+ "fresh_fetch"
+ ],
+ "type": "string"
+ },
+ "status": {
+ "maximum": 599,
+ "minimum": 100,
+ "type": "integer"
+ },
+ "url": {
+ "format": "uri",
+ "type": "string"
+ }
+ },
+ "required": [
+ "url",
+ "final_url",
+ "observed_at",
+ "age_seconds",
+ "status",
+ "content_hash",
+ "content_length",
+ "etag",
+ "last_modified",
+ "fetch_duration_ms",
+ "source",
+ "proof_id",
+ "receipt_hash"
+ ],
+ "type": "object"
+ },
+ "verification": {
+ "additionalProperties": false,
+ "properties": {
+ "checks": {
+ "items": {
+ "additionalProperties": false,
+ "properties": {
+ "actual": {
+ "description": "Observed value used by the rule."
+ },
+ "expected": {
+ "description": "Expected value or condition used by the rule."
+ },
+ "pass": {
+ "description": "Whether this individual rule passed.",
+ "type": "boolean"
+ },
+ "rule": {
+ "description": "Policy rule that was evaluated.",
+ "type": "string"
+ }
+ },
+ "required": [
+ "rule",
+ "pass",
+ "actual",
+ "expected"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "decision": {
+ "description": "Overall policy decision. PASS means every supplied rule passed; FAIL means at least one supplied rule failed; UNKNOWN means a reliable decision could not be made.",
+ "enum": [
+ "PASS",
+ "FAIL",
+ "UNKNOWN"
+ ],
+ "type": "string"
+ },
+ "proof_id": {
+ "description": "FreshProof proof identifier returned by observe_url or verify_url.",
+ "pattern": "^fp1_[a-f0-9]{64}$",
+ "type": "string"
+ },
+ "receipt": {
+ "additionalProperties": false,
+ "properties": {
+ "payload": {
+ "additionalProperties": false,
+ "properties": {
+ "content_hash": {
+ "pattern": "^sha256:[a-f0-9]{64}$",
+ "type": "string"
+ },
+ "content_length": {
+ "maximum": 9007199254740991,
+ "minimum": 0,
+ "type": "integer"
+ },
+ "etag": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "fetch_duration_ms": {
+ "maximum": 9007199254740991,
+ "minimum": 0,
+ "type": "integer"
+ },
+ "final_url": {
+ "format": "uri",
+ "type": "string"
+ },
+ "last_modified": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "method": {
+ "const": "GET",
+ "type": "string"
+ },
+ "normalized_url": {
+ "format": "uri",
+ "type": "string"
+ },
+ "observation_id": {
+ "type": "string"
+ },
+ "observed_at": {
+ "description": "ISO-8601 timestamp of the observation.",
+ "type": "string"
+ },
+ "original_url": {
+ "format": "uri",
+ "type": "string"
+ },
+ "status": {
+ "maximum": 599,
+ "minimum": 100,
+ "type": "integer"
+ },
+ "version": {
+ "const": "freshproof-receipt-v1",
+ "type": "string"
+ }
+ },
+ "required": [
+ "version",
+ "observation_id",
+ "normalized_url",
+ "original_url",
+ "final_url",
+ "observed_at",
+ "method",
+ "status",
+ "content_hash",
+ "content_length",
+ "etag",
+ "last_modified",
+ "fetch_duration_ms"
+ ],
+ "type": "object"
+ },
+ "proof_id": {
+ "description": "FreshProof proof identifier returned by observe_url or verify_url.",
+ "pattern": "^fp1_[a-f0-9]{64}$",
+ "type": "string"
+ },
+ "receipt_hash": {
+ "description": "SHA-256 content address of the canonical Proof Receipt payload.",
+ "pattern": "^sha256:[a-f0-9]{64}$",
+ "type": "string"
+ }
+ },
+ "required": [
+ "proof_id",
+ "receipt_hash",
+ "payload"
+ ],
+ "type": "object"
+ },
+ "valid": {
+ "description": "True when the stored receipt passes deterministic integrity verification.",
+ "type": "boolean"
+ }
+ },
+ "required": [
+ "proof_id",
+ "valid",
+ "decision",
+ "checks",
+ "receipt"
+ ],
+ "type": "object"
+ }
+ },
+ "required": [
+ "observation",
+ "verification"
+ ],
+ "type": "object"
+}verify_proofverify_urlfreshproof_infoobserve_url
Add one secure layer between your agents and this server.