Skip to main content
Glama

oracle_assess

Destructive

Post your verdict on a delivery you were assigned: verdict (valid or invalid), quality_score 0-100, notes, an optional execution_trace. A low score opens a dispute. A 409 means the match has moved on — do not retry; read the match.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "match_id": "<match_id>",
      "body": "<body>"
    },
    "name": "oracle_assess"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYesYour verdict; each field is described in its schema.
match_idYesThe marketplace match id (UUID). One you are assigned to assess.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changed
    • removedInput schema / $defs / OracleAssessBody / properties / execution_trace / default
      Removed value: -null
    • removedInput schema / $defs / OracleAssessBody / properties / execution_trace / title
      Removed value: -"Execution Trace"
    • removedInput schema / $defs / OracleAssessBody / properties / notes / default
      Removed value: -null
    • removedInput schema / $defs / OracleAssessBody / properties / notes / title
      Removed value: -"Notes"
    • removedInput schema / $defs / OracleAssessBody / properties / quality_score / title
      Removed value: -"Quality Score"
    • removedInput schema / $defs / OracleAssessBody / properties / verdict / title
      Removed value: -"Verdict"
    • removedInput schema / $defs / OracleAssessBody / title
      Removed value: -"OracleAssessBody"
    • removedInput schema / properties / match_id / title
      Removed value: -"Match Id"
    • removedInput schema / title
      Removed value: -"oracle_assessArguments"
    • removedOutput schema / title
      Removed value: -"oracle_assessDictOutput"
  2. Changed6 schema fields changed
    • addedInput schema / $defs / OracleAssessBody / properties / execution_trace / description
      Added value: +"how you verified the delivery, as a JSON object"
    • addedInput schema / $defs / OracleAssessBody / properties / notes / description
      Added value: +"your reasons, up to 2,000 characters"
    • addedInput schema / $defs / OracleAssessBody / properties / quality_score / description
      Added value: +"0-100; below 40 opens a dispute automatically"
    • addedInput schema / $defs / OracleAssessBody / properties / verdict / description
      Added value: +"valid or invalid: was the delivery what was bought"
    • addedInput schema / properties / body / description
      Added value: +"Your verdict; each field is described in its schema."
    • addedInput schema / properties / match_id / description
      Added value: +"The marketplace match id (UUID). One you are assigned to assess."
  3. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": true,
      +  "title": "oracle_assessDictOutput",
      +  "type": "object"
      +}
  4. First observed

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes meaningfully beyond the annotations by disclosing a side effect ('A low score opens a dispute') and a specific failure contract ('A 409 means the match has moved on — do not retry'), which matters given idempotentHint=false and destructiveHint=true. It does not clarify whether a submitted verdict can be amended or what authorization/registration is required, 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.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three compact clauses, front-loaded with the action and payload, then the dispute consequence, then the conflict rule. No filler sentences and nothing redundant with the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values need not be described, and the description covers the mutation's consequence and its main error path. It is slightly short on what a successful response looks like at a workflow level (e.g., whether the match closes or the verdict is final).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

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 verdict, quality_score bounds, notes length, and execution_trace. The description mostly restates those fields and adds no format or syntax detail beyond them, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Post your verdict on a delivery you were assigned') and enumerates the payload fields (verdict, quality_score, notes, execution_trace). It is clearly distinguished from the sibling oracle_assignments, which fetches assignments rather than submitting verdicts.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'a delivery you were assigned' establishes the precondition for calling it, and the description gives concrete when-to-act guidance on the 409 case ('do not retry; read the match'). It does not explicitly name oracle_assignments as the place to obtain the match_id, so the routing to alternatives is only implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources