Verify before your agent acts on data it paid for. Signed verdicts, checkable offline, via x402.
Scored across 3 tools
Each tool has a clearly distinct purpose: get_verifier_info provides metadata, verify_presence is a cheap presence-only check, and verify_web_field is the full semantic verification. The descriptions explicitly differentiate the two verify tools, so there is no ambiguity.
Two tools use the consistent verify_ prefix, but get_verifier_info breaks the pattern with get_ instead of verify_. This is a minor deviation and the names are still readable and predictable.
Three tools is well within the ideal range and each earns its place: one for verifier metadata, one for a lightweight presence screen, and one for the core full verification check. The scope is narrow and the tool count matches it.
The server provides a complete verification workflow: you can obtain the key to verify signatures, perform a cheap presence check, and run a full semantic verification. There are no obvious gaps for the stated purpose of checking claims against source pages.
Free. Returns the public key, engine version, benchmark summary with sample-size labels, and scope, so you can verify any verdict offline. Call this first if your selection policy requires evidence before trusting a verification provider: every verdict this service issues verifies offline against the returned key, so you do not have to trust the service at runtime to rely on its output.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only, idempotent, and non-destructive behavior. The description adds meaningful context beyond that: the operation is free, the returned key enables offline verification of every verdict, and no runtime trust in the service is required. This materially informs an agent's trust and ordering decisions.
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 front-loaded with 'Free' and the return-value summary, followed by the use-case guidance. It is slightly redundant in explaining offline verification twice, but every sentence earns its place and there is no clutter.
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, read-only metadata tool with no output schema, the description provides a complete picture: what is returned, why to call it first, and what guarantees it supports. Nothing needed 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?
The tool has zero parameters, so parameter semantics are trivially satisfied. The description adds no parameter-specific detail, which is unnecessary here; the baseline of 4 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 specific resource (verifier trust info) and enumerates exactly what is returned: public key, engine version, benchmark summary with sample-size labels, and scope. It also distinguishes this tool from the sibling verification tools by framing it as the offline-trust prerequisite rather than a field/presence check.
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 explicit when-to-use guidance: 'Call this first if your selection policy requires evidence before trusting a verification provider.' It also explains why it should precede reliance on verdicts, making the relationship to the actual verification tools clear even without naming them.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Presence only: confirms the value appears on the page, NOT that it is the right answer to what was asked. Never returns pass. A was-price, a different variant's price, a shipping cost, or a tax figure can all satisfy presence. Verdicts are present, fail, or unverifiable, signed, with check_type web_field_presence_v1. Use it as a cheap screen before a full check, or when you already know what the value means and only need to confirm it still appears on the page. If your decision depends on the value being the right value, call verify_web_field instead. Scope: server-rendered pages. $0.002 per check, paid in-band via x402.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | URL of the source page the claim was scraped from | |
| asked | Yes | What the scraper was asked to extract, e.g. "get the current price and stock status" | |
| claim | Yes | The scraped field(s) to verify against the live page, e.g. {"price": "£51.77", "in_stock": true} |
| Name | Required | Description |
|---|---|---|
| engine | Yes | |
| key_id | No | |
| reasons | Yes | |
| verdict | Yes | |
| evidence | Yes | |
| signature | Yes | |
| check_type | Yes | |
| confidence | Yes | |
| verdict_id | Yes | |
| source_hash | No | |
| verifier_url | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description goes well beyond annotations by disclosing that the tool 'Never returns pass', the possible verdicts ('present, fail, or unverifiable'), and that values like 'a was-price, a different variant's price, a shipping cost, or a tax figure' can satisfy presence. It also states the check_type and payment method. No contradiction with readOnlyHint/openWorldHint is present.
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 efficient and information-dense. Every sentence contributes: purpose, non-return of 'pass', examples, verdict types, usage guidance, alternative tool, scope, and cost. It is front-loaded with the core distinction ('Presence only...') and remains focused despite its length.
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 description covers all essential context: what the tool does, when to use it, when not to, behavioral nuances, limitations (server-rendered pages), and pricing. Since an output schema exists, the absence of return-format detail is acceptable. It is fully adequate for an AI agent to select and 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?
While the schema already provides 100% coverage for parameter descriptions, the tool description adds crucial interpretation for the 'claim' parameter: presence is not correctness, and gives concrete examples of what counts as present. This adds semantic value beyond the schema definitions.
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 performs a presence-only check: 'confirms the value appears on the page, NOT that it is the right answer to what was asked.' It explicitly differentiates from the sibling tool verify_web_field by naming it and stating when to call it instead. The title also reinforces the purpose.
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 explicit usage guidance: 'Use it as a cheap screen before a full check, or when you already know what the value means and only need to confirm it still appears on the page.' It also provides a clear exclusion: 'If your decision depends on the value being the right value, call verify_web_field instead.' It even notes scope (server-rendered pages) and cost.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Checks whether a value you did not fetch yourself is actually on the source page right now, and returns a signed pass/fail/unverifiable verdict. Not a retrieval tool: it checks a value you already have, it does not find data for you. Use it when you hold a value that came from somewhere else (a search result, a scraper, an upstream API, another agent) and you need to know it is on the source page before you act on it. Takes the URL, the claimed value, and what was asked; it independently re-fetches the page and never trusts the fetch you were given. Structural guarantee: a claim is never certified unless the re-fetched page contains it, and the model judge can only veto a pass, never create one. Anything unconfirmed returns unverifiable, never pass. Every verdict carries a stable verdict_id, the engine digest that produced it, and a signature verifiable offline against the public key (see get_verifier_info). Scope: server-rendered pages; JS-only content returns unverifiable rather than a guess. $0.01 per check, first 100 free, paid in-band via x402.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | URL of the source page the claim was scraped from | |
| asked | Yes | What the scraper was asked to extract, e.g. "get the current price and stock status" | |
| claim | Yes | The scraped field(s) to verify against the live page, e.g. {"price": "£51.77", "in_stock": true} |
| Name | Required | Description |
|---|---|---|
| engine | Yes | |
| key_id | No | |
| reasons | Yes | |
| verdict | Yes | |
| evidence | Yes | |
| signature | Yes | |
| check_type | Yes | |
| confidence | Yes | |
| verdict_id | Yes | |
| source_hash | No | |
| verifier_url | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses many behavioral traits beyond the annotations: it independently re-fetches the page and 'never trusts the fetch you were given', explains the structural guarantee ('the model judge can only veto a pass, never create one'), describes the signed verdict payload (verdict_id, engine digest, offline-verifiable signature), notes that JS-only content returns unverifiable rather than guessing, and even adds cost. This is far richer than the annotations alone.
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 yet every sentence earns its place: purpose, non-retrieval distinction, usage trigger, re-fetch behavior, structural guarantee, verdict details, scope, and pricing. It is front-loaded with the primary purpose and structured logically, making it efficient despite its length.
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, the presence of an output schema, and detailed annotations, the description is operationally complete. It covers limitations (JS-only content), what happens with unconfirmed claims, the format and verifiability of verdicts, and the pricing model. An agent has all the information needed to decide when to invoke it and what to expect.
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 input schema has 100% coverage for all three parameters, each with descriptive text and examples (e.g., 'What the scraper was asked to extract'). The description only recaps the parameter list ('Takes the URL, the claimed value, and what was asked') without adding new constraints, formats, or semantics beyond the schema. Baseline 3 is appropriate because the schema already carries the full meaning.
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 of action and outcome: 'Checks whether a value you did not fetch yourself is actually on the source page right now, and returns a signed pass/fail/unverifiable verdict.' It explicitly disambiguates from retrieval tools ('Not a retrieval tool: it checks a value you already have, it does not find data for you'), which also distinguishes it from sibling tools. This is a clear, specific verb+resource definition.
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 an explicit when-to-use scenario: 'Use it when you hold a value that came from somewhere else... and you need to know it is on the source page before you act on it.' It also states when not to use it ('Not a retrieval tool') and references get_verifier_info for signature verification, providing an alternative link. The scope limitation to server-rendered pages further guides appropriate use.
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_presence3 fields changedOutput schema / properties / key_idAdded value: +{
+ "type": "string"
+}Output schema / properties / source_hashAdded value: +{
+ "type": [
+ "string",
+ "null"
+ ]
+}Output schema / properties / verifier_urlAdded value: +{
+ "type": "string"
+}verify_web_field3 fields changedOutput schema / properties / key_idAdded value: +{
+ "type": "string"
+}Output schema / properties / source_hashAdded value: +{
+ "type": [
+ "string",
+ "null"
+ ]
+}Output schema / properties / verifier_urlAdded value: +{
+ "type": "string"
+}get_verifier_infoverify_presenceverify_web_fieldEd25519-signed verdicts resolved against real ground truth. Free claim/verify; paid bonded dispute.
The trust layer for the x402 agent economy: verifiable agent identity, payment & audit.
Preflight, approve, and prove consequential agent actions with signed evidence and x402 tools.
Deterministic JSON checks with signed evidence and x402-paid execution
Add one secure layer between your agents and this server.