Submit a compute job for verification by the Verification Fleet (4 agents). Returns Groth16-style proof. $0.001/proof in USDC.
| Name | Required | Description | Default |
|---|---|---|---|
| driver | Yes | Source driver: ionet | render | akash | aleo | custom | |
| job_id | Yes | Job ID to verify | |
| submitter_did | Yes | DID of the submitting agent | |
| claimed_output_hash | Yes | SHA-256 of claimed output |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / properties / claimRemoved value: -{
- "description": "Optional claim metadata (model_id, job_id, output_hash, ...)",
- "type": "object"
-}Input schema / properties / claimed_output_hashAdded value: +{
+ "description": "SHA-256 of claimed output",
+ "type": "string"
+}Input schema / properties / driverAdded value: +{
+ "description": "Source driver: ionet | render | akash | aleo | custom",
+ "type": "string"
+}Input schema / properties / job_idAdded value: +{
+ "description": "Job ID to verify",
+ "type": "string"
+}Input schema / properties / proofRemoved value: -{
- "description": "Groth16 proof envelope (dict {a,b,c} or 8-element list of BN254 field elements)"
-}Input schema / properties / proof_systemRemoved value: -{
- "description": "Proof system identifier (default 'groth16')",
- "type": "string"
-}Input schema / properties / public_inputsRemoved value: -{
- "description": "List of BN254 field elements (hex strings or ints)",
- "type": "array"
-}Input schema / properties / submitter_didAdded value: +{
+ "description": "DID of the submitting agent",
+ "type": "string"
+}Input schema / requiredPrevious value: -[
- "proof",
- "public_inputs"
-]New value: +[
+ "job_id",
+ "driver",
+ "claimed_output_hash",
+ "submitter_did"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It mentions the fleet size and cost, but omits critical behavioral details: whether the operation is synchronous, what happens on verification failure, required permissions/auth, and any side effects. For a submission/payment-triggering action, this is a significant 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 extremely concise: three short sentences that state the action, return value, and cost. Every sentence earns its place, with no filler or 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?
With no annotations or output schema, the description is the only source of behavioral context. It fails to explain error handling, response format beyond 'proof', whether the job submission is asynchronous, or any prerequisites. This is incomplete for a tool that initiates a paid verification process.
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 100%, so the schema already documents each parameter. The description adds no parameter-specific meaning, but it doesn't need to since the schema is complete. Baseline 3 is appropriate.
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 action ('Submit a compute job for verification') and the resource (Verification Fleet), and notes the return value (Groth16-style proof). It distinguishes from siblings (capacity/agents) by focusing on verification. However, the tool name 'verify_proof' suggests verifying a proof, while the description says submitting a job, which creates minor ambiguity.
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 implied: use this when you need to verify a compute job and obtain a proof. However, there is no explicit guidance on when not to use it or alternatives, and sibling tools are not mentioned.
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 has a clearly distinct purpose: capacity telemetry, agent roster, and proof verification. There is no overlap or ambiguity between them.
All tools follow the same computergrid_ verb_noun pattern, using snake_case consistently. The naming is predictable and easy to understand.
With only 3 tools, the server is concise and focused. While slightly on the lower end, each tool earns its place for the intended read-only/verification scope.
The server provides capacity, agent list, and proof verification, covering the core 'read-only + verify' domain. Minor gaps exist, such as no job status or history, but these are not critical for the stated purpose.