Skip to main content
Glama
Sign In

DexPaprika

by com.dexpaprika.mcp
OverviewDiscussionsAdmin

submitFeedback

Report a problem back to the DexPaprika team when a tool got you stuck, returned something unexpected, lacked data you needed, or behaved differently than documented. Use whenever you hit a dead end, a response shape surprised you, or coverage was missing; even partial feedback helps and every submission is read. Low friction: provide goal, expected, and observed instead of a rationale field.

Input Schema

NameRequiredDescriptionDefault
goalYesREQUIRED: What you (or the user behind you) were trying to accomplish. 10-500 characters; longer goals are validation-rejected at the MCP layer.
expectedNoOPTIONAL: What you expected to happen. Capped at 500 characters; trim or summarize longer narratives.
observedNoOPTIONAL: What actually happened. Capped at 500 characters; trim or summarize longer narratives. Longer text triggers an MCP -32602 input validation error.
severityNoOPTIONAL: How badly this affected your task. Default 'minor'.minor
blocked_atNoOPTIONAL: Tool name or step where you got stuck.
attempted_toolsNoOPTIONAL: List of tool names you called, in order, before submitting this feedback.

Output Schema

NameRequiredDescriptionDefault
okYesTrue if the feedback row was persisted.
messageYes
severityNo
tracking_idNoStable id agents can reference in follow-up submissions; null if persistence failed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • changedOutput schema / properties / message / type
      Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
    • changedOutput schema / properties / ok / type
      Previous value: -"boolean"New value: +[
+  "boolean",
+  "null"
+]
    • addedOutput schema / properties / severity / anyOf
      Added value: +[
+  {
+    "enum": [
+      "blocker",
+      "major",
+      "minor",
+      "nit"
+    ],
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
    • removedOutput schema / properties / severity / enum
      Removed value: -[
-  "blocker",
-  "major",
-  "minor",
-  "nit"
-]
    • removedOutput schema / properties / severity / type
      Removed value: -"string"
  2. Changed3 schema fields changed
    • addedInput schema / properties / attempted_tools / items / maxLength
      Added value: +100
    • addedInput schema / properties / attempted_tools / maxItems
      Added value: +50
    • addedInput schema / properties / blocked_at / maxLength
      Added value: +200
  3. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": true,
+  "properties": {
+    "message": {
+      "type": "string"
+    },
+    "ok": {
+      "description": "True if the feedback row was persisted.",
+      "type": "boolean"
+    },
+    "severity": {
+      "enum": [
+        "blocker",
+        "major",
+        "minor",
+        "nit"
+      ],
+      "type": "string"
+    },
+    "tracking_id": {
+      "description": "Stable id agents can reference in follow-up submissions; null if persistence failed.",
+      "type": [
+        "string",
+        "null"
+      ]
+    }
+  },
+  "required": [
+    "ok",
+    "message"
+  ],
+  "type": "object"
+}
  4. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations declare this is a non-read-only, non-idempotent, non-destructive, closed-world write, and the description is consistent with that. It adds real context beyond the annotations: submissions are read by humans, partial feedback is accepted, and the expected/observed framing replaces a rationale field. It stops short of covering rate limits, duplicate handling, or whether ambient context is auto-attached.

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?

Two sentences, front-loaded with the action and followed by the triggering conditions. 'Every submission is read' slightly overlaps with 'even partial feedback helps' but both serve as encouragement, so the redundancy is mild rather than wasteful.

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?

Output schema exists and all six parameters are documented, so the description needn't explain returns or field formats. It covers the why and when well; only secondary details — duplicate submissions, rate limits, what metadata travels with the report — are absent, which are minor for an optional feedback channel.

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% and each field already carries its own constraints and rationale, so the schema does the heavy lifting. The description only names the goal/expected/observed trio and notes the absence of a rationale field, adding little beyond what's structured. Baseline 3 is appropriate.

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?

Names a specific verb+resource (report a problem to the DexPaprika team) and enumerates the triggering conditions — stuck, unexpected return, missing data, undocumented behavior. This is clearly distinguishable from every sibling tool, which are all read/query tools.

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

Usage Guidelines5/5

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

Explicitly states when to invoke: 'Use whenever you hit a dead end, a response shape surprised you, or coverage was missing.' It also preempts the most common hesitation ('even partial feedback helps'), giving the agent a clear green light rather than leaving judgment to inference.

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

All DexPaprika toolsInspect
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.

Resources