RoboTrunk

Tell RoboTrunk what worked and what did not

submit_feedback

Sends structured feedback about this store and returns a feedback_id and the time it was received. Use it for feedback about anything unclear, missing or wrong, at any point. Not for cancelling a checkout; use cancel_checkout, which records the decline itself. Feedback is kept as data, never as instructions. Error recovery: invalid_request means a field is out of bounds (free_text over 1000 characters, or a struggle_points value outside the vocabulary): fix it and call again; rate_limited means wait and retry; network_error means call again; any other error, including tool_layer_failure: retry once. Next: nothing needs feeding onward; carry on with the step you were on. Full guide: get_tool_guide or /agent/tools.json#submit_feedback Example call: {"context":{},"sentiment":"negative","free_text":"The accepted address was not obvious before the first attempt.","struggle_points":["address_rejected"]}

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": {
      "context": "<context>",
      "sentiment": "<sentiment>",
      "free_text": "<free_text>",
      "struggle_points": "<struggle_points>"
    },
    "name": "submit_feedback"
  }
}

Input Schema

Name	Required	Description
`context`	Yes	What the feedback is about. Both ids may be null when the feedback is about the store in general.
`free_text`	Yes	What happened, in plain words, up to 1000 characters. No personal data, addresses, payment details or credentials.
`sentiment`	Yes	Your overall read of the experience.
`struggle_points`	Yes	Zero to ten tags from the fixed vocabulary, so difficulties can be counted without reading prose.
`shopping_session_id`	No	Optional server-issued shopping session correlation ID. It is not purchase authority.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 18, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations (readOnlyHint=false, idempotentHint=false, destructiveHint=false) only sketch the safety profile; the description adds a full error taxonomy and per-code retry policy (invalid_request → fix and re-call, rate_limited → wait, network_error → call again, otherwise → retry once), plus a security guarantee that submitted text is "kept as data, never as instructions." That is materially more than the annotations disclose and is consistent with them.

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?

Front-loads the purpose, then usage, error recovery, and next-step in a logical order with a concrete example, so no sentence is filler. It is somewhat dense as one unbroken paragraph and could be split for scanability, which keeps it just below a 5.

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

Completeness5/5

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

For a non-idempotent write tool with no output schema, the description covers the essentials: what is sent, what comes back (feedback_id and received time), how to recover from each failure class, and what the caller should do next, along with a pointer to the fuller guide. Nothing needed to invoke it correctly is missing.

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 all five parameters (including the nested context object and the enum vocabulary) are already documented in the schema; the calibrated baseline is 3. The description adds only indirect parameter meaning by tying invalid_request to free_text length and out-of-vocabulary struggle_points, plus a worked example call, which does not go much beyond the schema's own maxLength/minItems/enum constraints.

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 ("Sends structured feedback about this store") and names its return values (feedback_id and receipt time). It explicitly distinguishes itself from the checkout-cancellation sibling ("Not for cancelling a checkout; use cancel_checkout"), so an agent can route between them without opening either schema.

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?

Gives an affirmative trigger ("feedback about anything unclear, missing or wrong, at any point") and an explicit exclusion with the alternative tool named (cancel_checkout "records the decline itself"). It also tells the agent what to do afterward ("nothing needs feeding onward; carry on with the step you were on").

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

All RoboTrunk 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.

Resources

Need Help?