Galatic.ai

Concierge feedback

concierge_feedback

Act on a Concierge month that is waiting for the customer's review (see concierge_status). "revision" spends the month's one revision round: everything rated thumbs-down is regenerated in the background (202; a second request is refused with 409). "finalize" delivers the month to the gallery, leaving out items still rated down; it happens on its own after 5 days. "feedback" (contentType "image" or "video", index, rating "up" or "down", optional reason) rates one item; rate the items to redo "down" before asking for a revision. monthKey is "YYYY-MM".

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": {
      "action": "<action>",
      "monthKey": "<monthKey>",
      "context": "<context>",
      "llm_model": "<llm_model>"
    },
    "name": "concierge_feedback"
  }
}

Input Schema

Name	Required	Description
`index`	No	0-based position of the item within its contentType. For feedback.
`action`	Yes
`rating`	No	Thumbs up or down. For feedback.
`reason`	No	Optional note with the rating.
`context`	Yes	Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution."
`monthKey`	Yes	"YYYY-MM", e.g. "2026-10".
`llm_model`	Yes	The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.
`contentType`	No	For feedback.
`conversation_id`	No	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request.

Schema Changelog

Changes observed during successful MCP inspections.

Changed9 schema fields changedOct 26, 2026
- addedInput schema / properties / contentType / description
```
Added value: +"For feedback."
```
- addedInput schema / properties / contentType / enum
```
Added value: +[
+  "image",
+  "video"
+]
```
- addedInput schema / properties / index / description
```
Added value: +"0-based position of the item within its contentType. For feedback."
```
- changedInput schema / properties / index / minimum
```
Previous value: --9007199254740991New value: +0
```
- addedInput schema / properties / monthKey / description
```
Added value: +"\"YYYY-MM\", e.g. \"2026-10\"."
```
- addedInput schema / properties / rating / description
```
Added value: +"Thumbs up or down. For feedback."
```
- addedInput schema / properties / rating / enum
```
Added value: +[
+  "up",
+  "down"
+]
```
- changedInput schema / properties / rating / type
```
Previous value: -"number"New value: +"string"
```
- addedInput schema / properties / reason / description
```
Added value: +"Optional note with the rating."
```
First observedOct 24, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations only say non-read-only, non-destructive, non-idempotent; the description goes well beyond by disclosing the one-revision-round quota, that regeneration is asynchronous (202), that a duplicate revision is refused with 409, and that finalize silently excludes items still rated down. These are exactly the operational constraints an agent needs before invoking a mutating tool.

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-loaded with the precondition, then each action in a tight clause with no filler. It is dense to the point of reading as telegraphic fragments, which slightly hurts scanability, but every sentence carries real information.

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 9-parameter, three-mode mutation tool with no output schema, the description covers preconditions, side effects, quotas, and error behavior. Minor gaps remain — what a feedback call returns (e.g., current rating state) and any permission requirements — but nothing essential to calling 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 coverage is 89%, so contentType, index, rating, reason, and monthKey are already documented in the schema; the description largely restates those same bindings for the feedback action. It adds no semantics for context, llm_model, or conversation_id, so it does not exceed the schema baseline.

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 the resource (a Concierge month awaiting the customer's review) and spells out all three verbs with distinct concrete effects: 'revision' regenerates thumbs-down items, 'finalize' delivers to gallery, 'feedback' rates one item. It explicitly routes the agent to concierge_status as the discovery counterpart, distinguishing it from that sibling 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?

It states the precondition (a month waiting for review), gives a per-action when-to-use mapping, and adds an ordering rule: rate items 'down' before asking for a revision. It also notes finalize happens automatically after 5 days, which tells the agent when it need not call at all.

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

All Galatic.ai 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.