Legacy compatibility alias for prompt/response verification and existing MCP clients. Prefer oracle.verify_autonomous_action for new integrations.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | ||
| action | No | ||
| domain | No | ||
| policy | No | ||
| prompt | No | ||
| context | No | ||
| response | No | ||
| use_case | No | ||
| idempotency_key | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full disclosure burden. It reveals that the tool is a legacy alias and performs verification, but it does not explain what the verification returns, whether side effects or auth are involved, or how the two oneOf call patterns behave differently. The 'legacy' label is useful context, but too little behavioral substance is disclosed.
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 one tight sentence with no filler, and the most important routing information ('prefer oracle.verify_autonomous_action') is placed at the end after establishing legacy context. It is concise, though arguably too short to carry the full explanatory burden for such a complex schema.
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?
Given 9 parameters, a mutually exclusive oneOf schema, nested objects, no output schema, and no annotations, the description is not complete enough for an agent to invoke the tool correctly. It does provide the legacy/alternative context, but it omits the two invocation patterns, modes, and expected results. An agent would need external knowledge or trial and error to call this reliably.
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 description coverage is 0%, and the description only implies that 'prompt' and 'response' are the objects of verification. It says nothing about the use_case/action branch, the mode enum, idempotency_key, or policy/context semantics. This is minimal compensation for a complex oneOf schema, so the description adds little parameter-level value.
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 identifies the tool as a 'Legacy compatibility alias for prompt/response verification', giving a specific action and resource. It also distinguishes it from siblings by pointing to oracle.verify_autonomous_action as the preferred alternative. It stops short of a 5 because it uses the nominal 'verification' rather than a direct verb phrase, but the intent is clear.
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 explicitly states when to use this tool versus the alternative: it is for 'existing MCP clients' and legacy compatibility, while new integrations should prefer oracle.verify_autonomous_action. This gives an agent a concrete decision rule without needing to inspect either schema.
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.
Verification and trust receipt tools are clearly separated, but discovery_bundle, service_descriptor, and agent_card overlap as metadata discovery endpoints, and verify_response is a legacy alias next to verify_autonomous_action. Descriptions help, but an agent could hesitate when choosing among the metadata tools.
The oracle.* prefix and get_/verify_ action prefixes provide a mostly predictable pattern. However, agent_card, discovery_bundle, and service_descriptor are noun-style endpoints rather than verb_noun, creating minor inconsistency.
Nine tools is well-proportioned for the server's scope, covering discovery, pricing, verification, and trust receipt operations without unnecessary bloat. Each tool addresses a distinct part of the integration workflow.
The set covers the core workflow: discover capabilities, read pricing, perform single or batch verification, and resolve or verify trust receipts. Minor gaps exist around explicit account balance or allowance management, but pricing and top-up metadata partially address that need.