Free. Current state of a verification by checkId; re-checks it once its retry or challenge time has passed.
| Name | Required | Description | Default |
|---|---|---|---|
| checkId | Yes | ||
| requiredLevel | No | Proof level you need before releasing money (Base: tee_attested < zk_proven < resolved; Ethereum: finalized; XRPL: unl_quorum). The answer then says whether it is releasable. |
Changes observed during successful MCP inspections.
Input schema / properties / requiredLevel / descriptionPrevious value: -"Proof level you need before releasing money (Base: tee_attested < zk_proven < resolved; Ethereum: finalized). The answer then says whether it is releasable."New value: +"Proof level you need before releasing money (Base: tee_attested < zk_proven < resolved; Ethereum: finalized; XRPL: unl_quorum). The answer then says whether it is releasable."Input schema / properties / requiredLevel / enumPrevious value: -[
- "tee_attested",
- "zk_proven",
- "resolved",
- "finalized"
-]New value: +[
+ "tee_attested",
+ "zk_proven",
+ "resolved",
+ "finalized",
+ "unl_quorum"
+]Input schema / properties / requiredLevelAdded value: +{
+ "description": "Proof level you need before releasing money (Base: tee_attested < zk_proven < resolved; Ethereum: finalized). The answer then says whether it is releasable.",
+ "enum": [
+ "tee_attested",
+ "zk_proven",
+ "resolved",
+ "finalized"
+ ],
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations the description carries the full burden, and it does disclose two useful traits: the call is free and it may internally re-check once a retry/challenge time has elapsed. It does not mention auth requirements, whether the re-check has side effects beyond the read, rate limits, or what the state payload looks like.
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 compact statements with the cost attribute ('Free.') front-loaded and the core purpose immediately following. No wasted words, though the semicolon clause packs two ideas into one sentence.
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 multi-chain verification-status tool with no output schema and no annotations, the description is serviceable but thin: it omits return payload shape, the meaning of releasability relative to requiredLevel, and any auth/ownership requirements. The 'free' and re-check details partially compensate.
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 50%. checkId is named in the description but given no extra meaning beyond the schema, and requiredLevel — the parameter whose ordering across Base/Ethereum/XRPL determines releasability — is documented only in the schema, not reinforced or clarified in the description. Baseline 3 for a mid-coverage schema fits.
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?
States a specific verb+resource: retrieving the current state of a verification identified by checkId. It also discloses that the check is re-run once a retry/challenge window has passed, which sharpens what the call actually returns. It does not explicitly distinguish itself from siblings get_verifications or watch_verification, so it stops short of 5.
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?
Usage is only implied: 'current state ... by checkId' plus the re-check timing signals a polling pattern for a single verification. It never says when to prefer this over watch_verification (streaming) or get_verifications (bulk), nor states prerequisites such as owning the check.
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.