Trent

Remove feedback notes

remove_feedback

DestructiveIdempotent

Remove several feedback items in one operation. Removal is permanent. To correct an item instead, use update_feedback.

Use identifiers from known items, such as a prior list_feedback result.
Do not guess or reconstruct identifiers; they select the items to remove.
The call succeeds even with mixed item outcomes: removed,
already_removed, not_found, or failed. Read summary and results to learn
what happened to each item.

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": {
      "feedback_ids": "<feedback_ids>"
    },
    "name": "remove_feedback"
  }
}

Input Schema

Name	Required	Description
`project_id`	No	Project ID (provide either project_id or project_name)
`feedback_ids`	Yes	The feedback items to remove, up to 50 per call. A call over that bound is rejected and nothing is written.
`project_name`	No	Project name (provide either project_id or project_name)

Output Schema

Name	Required	Description
`error`	No	True when the call itself failed. False for successful calls, including a scan still running, an already approved plan, or a repository classified as non-agentic. The reason field describes these workflow states.
`reason`	No	A stable snake_case code from the allowed set. Present on every error and on successful calls that carry a workflow state.
`message`	No	Exactly one sentence written for the user. Never raw exception text or a backend error string, which may expose private details.
`results`	No	One {feedback_id, outcome} result per distinct identifier sent, in request order. outcome is 'removed', 'already_removed', 'not_found' (covers both a missing identifier and one belonging to another tenant), or 'failed'.
`summary`	No	Result counts for all four outcomes, including zeros. The call succeeds regardless of individual outcomes. Read summary and results to learn which items were removed.
`metadata`	No	Caller metadata, such as 'expiration_warning'. Substantive results have their own fields. Never includes exception or backend error text, which may expose private details.
`next_steps`	No	Recommended next actions, in order.
`operation_id`	No	The identifier every row this call redacted now carries, shared by the audit event for the operation.
`retry_after_seconds`	No	With reason rate_limited, how many seconds Trent asks the caller to wait.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 30, 2026

addedOutput schema / properties / retry_after_seconds

Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "With reason rate_limited, how many seconds Trent asks the caller to wait.",
+  "title": "Retry After Seconds"
+}

First observedOct 23, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered; the description still adds the non-obvious behavior that the call succeeds with mixed per-item outcomes (removed, already_removed, not_found, failed) and that the caller must read summary and results. That partial-success semantics is exactly the kind of context annotations cannot express.

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?

Five short sentences, front-loaded with the destructive action and the alternative sibling before the identifier guidance and outcome semantics. Each sentence carries a distinct fact — permanence, alternative, input provenance, partial-failure behavior — with no filler.

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?

An output schema exists, so the description is not obligated to detail return values, yet it still tells the agent which fields to inspect after a mixed-result call. For a destructive batch tool it covers scope, irreversibility, input requirements, and failure semantics — nothing an agent needs is missing.

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?

Schema coverage is 100% and the schema already documents the 50-item bound and the project_id/project_name pairing, so the description need not repeat it. It does add meaning beyond the schema by explaining what feedback_ids semantically select and where valid identifiers must come from (a prior list_feedback result), which the schema does not say.

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?

The description names a specific verb and resource ('Remove several feedback items in one operation') and immediately states the permanence of the effect. The batch scope ('several ... in one operation') separates it cleanly from single-item siblings and from update_feedback, which it names explicitly.

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?

It gives an explicit alternative and the condition selecting it ('To correct an item instead, use update_feedback'), plus a prerequisite-and-source rule ('Use identifiers from known items, such as a prior list_feedback result') and a prohibition ('Do not guess or reconstruct identifiers'). Both the when-to-use and how-to-prepare guidance are stated, not implied.

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

All Trent 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.