Fact-check personalized sales, recruiting, partnership, or outreach copy against supplied evidence and block unsupported claims before an automated send.
| Name | Required | Description | Default |
|---|---|---|---|
| draft | Yes | ||
| evidenceText | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the behavioral disclosure burden. It clearly states that it checks claims and blocks unsupported ones, but it does not explain what 'block' returns or how it signals pass/fail, nor whether the tool mutates state. This is adequate but not fully transparent.
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?
A single sentence that is dense but not bloated: it states the action, the target, the evidence source, the blocking behavior, and the timing. Every clause 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 simple two-string tool with no output schema, the description covers the core inputs and the intended gate behavior. It does not detail the return contract or what exactly happens when a claim is blocked, but the semantics are inferable for an agent deciding whether to call 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?
Schema coverage is 0% and the schema only names draft and evidenceText. The description compensates by mapping 'personalized ... copy' to draft and 'supplied evidence' to evidenceText, making both parameters meaningful beyond their names.
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 names a specific action ('fact-check' and 'block') and a specific resource ('personalized sales, recruiting, partnership, or outreach copy'). It clearly distinguishes this from sibling tools like verify_commercial_truth or commercial_terms_diff by focusing on pre-send personalization copy validation.
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 a clear context of use: before an automated send, when there is personalized copy and supporting evidence. It does not explicitly name alternatives or exclusion conditions, but the timing and purpose are unambiguous.
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.
Most tools have clearly distinct targets—Base reads, web research, opportunity search, and gating—but a few overlapping 'verify' and 'gate' tools could blur boundaries for an agent, especially verify_commercial_truth and verify_deadline_eligibility. Descriptions do differentiate them, so misuse is unlikely with careful prompting.
All names use snake_case and are internally consistent for the base_* cluster, but outside of that, some tool names are nouns while others are verbs (e.g., domain_intelligence, web_read, vendor_verification). This mixed convention makes it less predictable than a strict verb_noun pattern.
21 tools is on the high side of the comfortable range, but the server covers a broad scope: blockchain reads, web/content intelligence, opportunity discovery, commercial verification, and preflight gates. Each tool has a distinct role, though a few feel marginal rather than essential for a leaner setup.
The set covers the main workflows you'd expect: reading blockchain state, researching and verifying web snippets, tracking opportunities, and blocking bad actions with a fee preflight. The notable gap is an explicit execution step—there is no actual sending, bidding, or payment action beyond the x402 preflight. That is a reasonable boundary for a read/preflight tool suite.