verify_web_evidenceVerify one public URL and return timestamped status, redirects, metadata, content hash, and a receipt.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | ||
| expectedText | No | ||
| expectedStatus | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds useful behavioral context by specifying that results are timestamped and that a receipt is produced, plus the implicit restriction to 'public' URLs. However, the $0.01 USDC cost is a significant behavioral trait that is absent from the description and only appears in the title.
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, efficient sentence that front-loads the action and then lists the return payload. There is no redundancy or filler. It could earn a 5 if it had folded in the cost or usage conditions, but as written it is appropriately tight.
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 explains what the tool returns, which helps given there is no output schema. But it leaves out critical invocation context: how expectedText/expectedStatus affect verification, when to pick this tool over siblings, and the monetary cost (present only in the title). It is adequate but has clear gaps.
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 gives only types/formats for url, expectedText, and expectedStatus, with no semantic descriptions, so schema_description_coverage is essentially zero. The description does not explain what expectedText or expectedStatus mean for the verification, nor how they modify the behavior. Only 'url' is implicitly covered by 'one public URL'.
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 ('Verify') with a concrete resource ('one public URL') and enumerates the outputs (timestamped status, redirects, metadata, content hash, receipt). It is clearly not a generic list or snapshot tool, and the singular 'one public URL' helps separate it from the sibling check_urls, though it never names that sibling explicitly.
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?
There is no explicit when-to-use or when-not-to-use guidance, and no alternatives are named. The phrase 'one public URL' implies a scope limit but does not tell the agent when to prefer verify_web_evidence over check_urls, snapshot, or archive. The cost signal lives only in the title, not in the description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Tools are mostly distinct. batch_check_urls and verify_web_evidence both involve URLs, but one is multi-URL health checking while the other is single-URL evidence verification with receipts. merchant_snapshot and treasury_preflight occupy clearly separate payment-intelligence domains.
All names use snake_case, but the pattern is mixed: two are verb-first (batch_check_urls, verify_web_evidence) and two are object-first (merchant_snapshot, treasury_preflight). This is readable but not fully predictable.
Four tools is well-scoped for a paid utility server. Each tool covers a distinct, useful capability without redundancy or bloat.
The surface covers batch and single URL checks, evidence verification, merchant diagnostics, and payment preflight. Minor gaps exist, such as no simple single-URL status-only check or merchant follow-up action, but the set feels intentionally scoped.