Keryx

Read feedback for your original answer

research_feedback_read

Read-onlyIdempotent

Original-caller private opinion on the exact delivered ordinary research answer. Requires its private bearer capability; a public report ID or link grants no authority. First choice is retained, exact retries are idempotent. Silence is no response. No research, source fetching, revision execution, refunds, signing or payments.

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": {
      "token": "<token>"
    },
    "name": "research_feedback_read"
  }
}

Input Schema

Name	Required	Description	Default
`token`	Yes	Private capability received with your original completed answer. Keep it out of reports, prompts to Keryx research, public links and exports.

Output Schema

Name	Required	Description	Default
`runId`	Yes
`format`	Yes
`feedback`	Yes
`execution`	Yes
`deliveredDigest`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 7, 2026

changedOutput schema / properties / feedback / anyOf

Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "choice": {
-        "enum": [
-          "useful",
-          "revise",
-          "reject"
-        ],
-        "type": "string"
-      },
-      "deliveredDigest": {
-        "$ref": "#/properties/deliveredDigest"
-      },
-      "format": {
-        "const": "keryx-requester-feedback-v1",
-        "type": "string"
-      },
-      "observations": {
-        "additionalProperties": false,
-        "properties": {
-          "costBasis": {
-            "const": "partial-captured-policy-estimate",
-            "type": "string"
-          },
-          "durationBasis": {
-            "const": "recorded-orchestrator-completion",
-            "type": "string"
-          },
-          "excluded": {
-            "const": "search-infrastructure-gas-and-unrecorded-provider-charges",
-            "type": "string"
-          },
-          "failedCalls": {
-            "minimum": 0,
-            "type": "integer"
-          },
-          "format": {
-            "const": "keryx-recorded-job-observations-v1",
-            "type": "string"
-          },
-          "generationDurationMs": {
-            "anyOf": [
-              {
-                "minimum": 0,
-                "type": "integer"
-              },
-              {
-                "type": "null"
-              }
-            ]
-          },
-          "invoice": {
-            "type": "null"
-          },
-          "missingUsageCalls": {
-            "minimum": 0,
-            "type": "integer"
-          },
-          "modelCostUsd": {
-            "anyOf": [
-              {
-                "additionalProperties": false,
-                "properties": {
-                  "lower": {
-                    "minimum": 0,
-                    "type": "number"
-                  },
-                  "upper": {
-                    "minimum": 0,
-                    "type": "number"
-                  }
-                },
-                "required": [
-                  "lower",
-                  "upper"
-                ],
-                "type": "object"
-              },
-              {
-                "type": "null"
-              }
-            ]
-          },
-          "pendingCalls": {
-            "minimum": 0,
-            "type": "integer"
-          },
-          "profit": {
-            "type": "null"
-          },
-          "recordedCalls": {
-            "minimum": 0,
-            "type": "integer"
-          },
-          "unpricedUsageRecords": {
-            "minimum": 0,
-            "type": "integer"
-          },
-          "usageRecords": {
-            "minimum": 0,
-            "type": "integer"
-          }
-        },
-        "required": [
-          "format",
-          "generationDurationMs",
-          "durationBasis",
-          "modelCostUsd",
-          "costBasis",
-          "recordedCalls",
-          "failedCalls",
-          "pendingCalls",
-          "missingUsageCalls",
-          "unpricedUsageRecords",
-          "usageRecords",
-          "excluded",
-          "invoice",
-          "profit"
-        ],
-        "type": "object"
-      },
-      "reason": {
-        "default": "",
-        "maxLength": 1000,
-        "type": "string"
-      },
-      "runId": {
-        "$ref": "#/properties/runId"
-      },
-      "submittedAt": {
-        "format": "date-time",
-        "type": "string"
-      }
-    },
-    "required": [
-      "choice",
-      "format",
-      "runId",
-      "deliveredDigest",
-      "submittedAt",
-      "observations"
-    ],
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "choice": {
+        "description": "Your opinion of this exact delivered answer: useful, revise or reject.",
+        "enum": [
+          "useful",
+          "revise",
+          "reject"
+        ],
+        "type": "string"
+      },
+      "deliveredDigest": {
+        "$ref": "#/properties/deliveredDigest"
+      },
+      "format": {
+        "const": "keryx-requester-feedback-v1",
+        "type": "string"
+      },
+      "observations": {
+        "additionalProperties": false,
+        "properties": {
+          "costBasis": {
+            "const": "partial-captured-policy-estimate",
+            "type": "string"
+          },
+          "durationBasis": {
+            "const": "recorded-orchestrator-completion",
+            "type": "string"
+          },
+          "excluded": {
+            "const": "search-infrastructure-gas-and-unrecorded-provider-charges",
+            "type": "string"
+          },
+          "failedCalls": {
+            "minimum": 0,
+            "type": "integer"
+          },
+          "format": {
+            "const": "keryx-recorded-job-observations-v1",
+            "type": "string"
+          },
+          "generationDurationMs": {
+            "anyOf": [
+              {
+                "minimum": 0,
+                "type": "integer"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "invoice": {
+            "type": "null"
+          },
+          "missingUsageCalls": {
+            "minimum": 0,
+            "type": "integer"
+          },
+          "modelCostUsd": {
+            "anyOf": [
+              {
+                "additionalProperties": false,
+                "properties": {
+                  "lower": {
+                    "minimum": 0,
+                    "type": "number"
+                  },
+                  "upper": {
+                    "minimum": 0,
+                    "type": "number"
+                  }
+                },
+                "required": [
+                  "lower",
+                  "upper"
+                ],
+                "type": "object"
+              },
+              {
+                "type": "null"
+              }
+            ]
+          },
+          "pendingCalls": {
+            "minimum": 0,
+            "type": "integer"
+          },
+          "profit": {
+            "type": "null"
+          },
+          "recordedCalls": {
+            "minimum": 0,
+            "type": "integer"
+          },
+          "unpricedUsageRecords": {
+            "minimum": 0,
+            "type": "integer"
+          },
+          "usageRecords": {
+            "minimum": 0,
+            "type": "integer"
+          }
+        },
+        "required": [
+          "format",
+          "generationDurationMs",
+          "durationBasis",
+          "modelCostUsd",
+          "costBasis",
+          "recordedCalls",
+          "failedCalls",
+          "pendingCalls",
+          "missingUsageCalls",
+          "unpricedUsageRecords",
+          "usageRecords",
+          "excluded",
+          "invoice",
+          "profit"
+        ],
+        "type": "object"
+      },
+      "reason": {
+        "default": "",
+        "description": "Optional private explanation of your choice, up to 1000 characters; defaults to empty.",
+        "maxLength": 1000,
+        "type": "string"
+      },
+      "runId": {
+        "$ref": "#/properties/runId"
+      },
+      "submittedAt": {
+        "format": "date-time",
+        "type": "string"
+      }
+    },
+    "required": [
+      "choice",
+      "format",
+      "runId",
+      "deliveredDigest",
+      "submittedAt",
+      "observations"
+    ],
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]

AddedOct 24, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already establish readOnly, idempotent, openWorld, and non-destructive, yet the description adds genuinely new behavioral facts: authority comes only from the private bearer capability and a public report ID or link grants none, exact retries are idempotent, and silence means no response. That auth and empty-result semantics go meaningfully beyond the annotation set, though the meaning of 'first choice is retained' remains unexplained.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

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

Information is front-loaded onto the resource definition, and the exclusion list is compressed into one efficient closing clause. A few fragments ('Silence is no response', 'First choice is retained') are terse to the point of ambiguity, which costs a little clarity.

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?

For a single-parameter read tool with an output schema and full annotation coverage, the definition supplies the key missing pieces: authentication model, idempotency of retries, and the empty-result condition. The remaining gap is the unexplained 'first choice is retained' clause, whose consequence for callers is not spelled out.

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

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With a single parameter and 100% schema description coverage, the schema already carries the basic meaning, so the baseline is 3. The description earns an increment by reinforcing the security semantics of the token — that it is a private capability and no public identifier substitutes for it — which matches and strengthens the schema's handling notes.

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

Purpose4/5

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

The description identifies a specific resource: the original caller's private opinion (feedback) on the exact delivered research answer, which cleanly separates it from the sibling research_feedback_submit. The verb is only implied by the title rather than stated in the description, and 'ordinary research answer' is slightly opaque, so it falls short of a full 5.

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

Usage Guidelines3/5

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

It conveys the precondition (you must be the original caller holding the private bearer capability) and lists a set of excluded purposes (no research, source fetching, revision execution, refunds, signing, payments), which effectively routes the agent away from the wrong tool. However, it never states positively when to call this versus siblings like deliverable_acceptance_read or history_read, so usage is inferred rather than instructed.

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

All Keryx tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.