Recompute a service's full receipt hash chain and fee ledger. Any party can audit Viridis Verified from receipts alone.
| Name | Required | Description | Default |
|---|---|---|---|
| service_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden. It mentions 'recompute' (suggesting a read-only verification) and explicitly states 'Any party can audit,' which implies no special permissions. However, it does not disclose potential costs, rate limits, or side effects, leaving some gaps.
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?
Two sentences, front-loaded with action, zero wasted words. It efficiently conveys purpose and accessibility without redundancy.
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 tool is simple (one optional-context parameter, output schema provided). The description covers purpose, audience, and scope ('full receipt hash chain and fee ledger'). It could mention how it relates to get_receipt, but given the output schema exists, it is sufficiently complete.
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 description does not explicitly define 'service_id,' but 'a service's full receipt hash chain' indicates the parameter identifies which service to verify. With only one parameter, the meaning is inferable, though not enriched beyond the schema.
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 function: 'Recompute a service's full receipt hash chain and fee ledger.' It uses a specific verb ('recompute') and names the exact resource ('receipt hash chain and fee ledger'), distinguishing it from siblings like get_receipt (which likely fetches a receipt) and register_service.
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 phrase 'Any party can audit Viridis Verified from receipts alone' provides clear context that this is an auditing tool usable by anyone, implying it is appropriate for verification purposes. It doesn't explicitly name alternative tools or exclusions, but the context is strong enough.
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 distinct purposes: call_verified, register_service, get_receipt, and verify_receipts are clearly separate. list_services and service_stats overlap in exposing call counts and fees, but one is a fleet-wide view while the other is a single-service detail, so confusion is unlikely with descriptions.
Tool names follow a consistent snake_case verb_noun pattern (call_verified, register_service, get_receipt, verify_receipts). However, 'service_stats' deviates slightly from the verb-first convention (could be get_service_stats), and 'call_verified' uses an adjective rather than a clear noun, making the pattern less uniform.
With 7 tools, the server is well-scoped for its purpose. Each tool covers a necessary aspect of the relay service: registration, invocation, receipt retrieval, stats, and auditing, without unnecessary bloat or missing core functions.
The core workflow (register a service, call it, verify receipts, fetch stats) is fully covered. Minor gaps exist: there is no update or deregistration for services, and no way to list all receipts without knowing IDs, but these are edge cases that can be worked around via service_stats and verify_receipts.