Free URL preflight. Cited text via separate paid Stripe MPP API.
Scored across 2 tools
The two tools are clearly distinct: proof_fetch_offer explains the paid offer and request schema without purchasing, while proof_fetch_preflight checks a URL's fetchability and provenance before any purchase. No ambiguity exists between them.
Both tools follow a consistent 'proof_fetch_' prefix with a noun suffix ('offer' and 'preflight'), creating a predictable and uniform naming pattern.
With only two tools, the server feels thin for its stated purpose of cited web evidence extraction. The count is borderline and does not fully cover the intended scope.
The tool surface lacks the core operation of actually fetching or extracting cited evidence. The preflight check and offer description are useful but do not enable the primary workflow, making the set severely incomplete.
Read the $0.50-per-successful-extraction offer and request schema without buying. Paid cited text uses POST /v1/evidence with Stripe MPP and a caller-generated idempotency key, only with buyer payment authority. Example arguments: {}.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and idempotentHint, and the description aligns with these without contradiction. It adds context about the paid POST /v1/evidence endpoint, but this is tangential to the tool's own behavior and does not disclose additional traits like return format or errors.
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 reasonably concise but includes a sentence about the paid endpoint that is not directly about this tool, and the example arguments duplicate the schema. Some trimming would improve focus.
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 simple read-only tool with no parameters and no output schema, the description covers the core purpose and provides enough context about the offer. Missing details like return format are not critical given the simplicity.
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 the baseline is 4. The description's 'Example arguments: {}' is redundant with the empty schema but does not mislead.
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 reads the $0.50-per-successful-extraction offer and request schema without buying, specifying a concrete verb and resource. It distinguishes from buying but does not explicitly differentiate from the sibling tool proof_fetch_preflight.
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 guidance is provided on when to use this tool versus the sibling proof_fetch_preflight or when to avoid it. The phrase 'without buying' implies an alternative but does not name it or explain conditions for use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Start here: check a public URL before buying cited extraction. Returns fetchability, provenance, hashes and deterministic injection indicators, not page text or a safety guarantee. No payment or purchase. Example: {"url":"https://example.com/","maxChars":30000}.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Public HTTP(S) document URL. No credentials, private networks, authenticated pages or browser rendering. | |
| maxChars | No | Maximum normalized characters to extract. Free preflight returns metadata only, never the extracted text. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish read-only, idempotent, open-world, and non-destructive behavior. The description adds context beyond that by specifying what it returns (metadata, not content) and explicitly denying a safety guarantee, which is a valuable behavioral clarification. No contradiction with 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?
The description is three concise sentences, each adding distinct value: the purpose and start-here directive, the return-type clarification and free nature, and a concrete example. It is front-loaded with the critical usage instruction and avoids any fluff.
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 simple preflight tool with rich annotations and fully documented parameters, the description covers usage, return contents, limitations, and an example. It could specify the exact output structure, but the listed metadata fields are sufficient for an agent to know what to expect. The lack of an output schema does not hinder 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 both parameters have detailed descriptions (e.g., 'Public HTTP(S) document URL. No credentials, private networks...' and maxChars limits). The description only provides an example usage, which adds marginal value. The schema carries the semantic weight, so the baseline of 3 is appropriate.
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: 'check a public URL before buying cited extraction' and enumerates the returned metadata (fetchability, provenance, hashes, deterministic injection indicators). It explicitly distinguishes itself from the paid sibling by saying 'No payment or purchase' and 'not page text or a safety guarantee.' This leaves 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?
'Start here' and 'before buying cited extraction' provide explicit guidance on when to use this tool. The warning that it does not return page text or a safety guarantee tells the agent what not to expect, and the free/no-payment note sets it apart from the sibling tool. This is strong, actionable usage guidance.
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.
proof_fetch_offer1 field changedInput schema / propertiesAdded value: +{}proof_fetch_preflight4 fields changedInput schema / properties / maxChars / descriptionAdded value: +"Maximum normalized characters to extract. Free preflight returns metadata only, never the extracted text."Input schema / properties / maxChars / examplesAdded value: +[
+ 30000
+]Input schema / properties / url / descriptionAdded value: +"Public HTTP(S) document URL. No credentials, private networks, authenticated pages or browser rendering."Input schema / properties / url / examplesAdded value: +[
+ "https://example.com/"
+]proof_fetch_offerproof_fetch_preflightFetch a URL and get clean Markdown with metadata. No API key required; rate-limited per IP.
Link-preview metadata and clean page-to-Markdown for any public URL. No install.
Zero-signup anonymous link-unfurl API. One GET returns clean JSON metadata for any public URL.
Same link preview data as link-preview-api, ~1/3 the price via a shared cache.
Add one secure layer between your agents and this server.
