Pre-audit a payment-gated endpoint before you buy from it. Two tiers, neither of which pays the endpoint: a live unpaid probe (challenge parse, scheme, latency, per-probe pass/fail, endpoint grade), and the on-chain settlement history of the offer's payee (has this address ever actually collected, how recently, how often). [paid: $0.50 USDC on Base]
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | http(s) URL to probe. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must carry the full burden. It transparently discloses that neither tier pays the endpoint (live unpaid probe), describes the data returned (challenge parse, scheme, latency, pass/fail, grade, settlement history), and states the tool's own cost ($0.50 USDC). This is substantive and honest, though it could explicitly state read-only nature or any side effects, which is a minor gap.
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 but efficient: one sentence states the purpose, a second breaks down the two tiers with parenthetical detail, and a bracketed note covers pricing. Every clause earns its place; no filler. It is front-loaded with the core task before elaborating.
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?
No output schema exists, so the description must explain both return values and usage context. It does so thoroughly: it lists the specific outputs of each tier, clarifies that the probe is unpaid, and states the cost. For a tool with a single parameter and a fifth of the description, this is fully sufficient for an agent to call it 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?
The schema covers the single parameter 'url' at 100%, so the baseline is 3. The description adds only contextual framing ('payment-gated endpoint') rather than deeper semantic information about the parameter itself, such as format or constraints, so it does not exceed the baseline.
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 specific verb ('Pre-audit') and a concrete resource ('a payment-gated endpoint'), immediately distinguishing it from siblings like get_risk_snapshot or get_alerts. It then enumerates the two tiers of output (live probe and on-chain settlement history), making its function unambiguous.
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?
It clearly states when to use the tool ('before you buy from it'), giving a concrete trigger condition. However, it does not explicitly contrast with alternatives or state when not to use it, so it falls short of the 5-level bar of explicit when/when-not/alternatives.
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.
Each tool targets a distinct concern: counterparty pre-audit, alerts, machine hazard index, market regime, and composite snapshot. There is no meaningful overlap; even similar risk metrics are clearly differentiated by scope (regime vs. snapshot).
All tools follow a verb_noun pattern with snake_case, mostly using the verb 'get' (get_alerts, get_mhi, get_regime, get_risk_snapshot). One tool uses 'check_counterparty' instead, a minor deviation that does not significantly harm predictability.
Five tools is well-scoped for a risk oracle server. Each tool provides a distinct piece of risk information without redundancy or bloat, fitting firmly in the ideal 3-15 range.
The tool surface covers the primary read operations for a risk oracle: counterparty checks, alerts, hazard index, regime, and composite scores. Minor gaps exist, such as historical trend retrieval or detailed dimension breakdowns per endpoint, but the core workflows are supported.