Skip to main content
Glama

crashtestyourstrategy

Submit structured feedback

submit_feedback

USE WHEN something in a response was wrong, unclear or missing and you want to tell the operator. Persists structured feedback on a previous response: your agent identity, the request_id, and items {category, severity, observation, suggested_action?, agent_confidence 0..1}. Aggregates are readable at feedback://insights.

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": {
      "agent_name": "<agent_name>",
      "feedback_items": "<feedback_items>",
      "overall_confidence": "<overall_confidence>"
    },
    "name": "submit_feedback"
  }
}

Input Schema

NameRequiredDescriptionDefault
agent_nameYesYour agent identity (model or product name).
request_idNorequest_id of the response this feedback refers to.
agent_vendorNoVendor of the submitting agent (e.g. 'Anthropic', 'OpenAI').
feedback_itemsYesOne or more items, each {category (FeedbackCategory ontology), severity, observation, suggested_action?, agent_confidence (0..1)}.
session_contextNoOptional free-text context of the session/workflow the feedback arose in.
overall_confidenceYesOverall confidence in this feedback, 0..1.
platform_version_evaluatedNoSchema/platform version the feedback refers to (e.g. 'ctys-agent-v1').

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / additionalProperties
      Added value: +false
  2. Changed7 schema fields changed
    • addedInput schema / properties / agent_name / description
      Added value: +"Your agent identity (model or product name)."
    • addedInput schema / properties / agent_vendor / description
      Added value: +"Vendor of the submitting agent (e.g. 'Anthropic', 'OpenAI')."
    • addedInput schema / properties / feedback_items / description
      Added value: +"One or more items, each {category (FeedbackCategory ontology), severity, observation, suggested_action?, agent_confidence (0..1)}."
    • addedInput schema / properties / overall_confidence / description
      Added value: +"Overall confidence in this feedback, 0..1."
    • addedInput schema / properties / platform_version_evaluated / description
      Added value: +"Schema/platform version the feedback refers to (e.g. 'ctys-agent-v1')."
    • addedInput schema / properties / request_id / description
      Added value: +"request_id of the response this feedback refers to."
    • addedInput schema / properties / session_context / description
      Added value: +"Optional free-text context of the session/workflow the feedback arose in."
  3. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=false, so safety is covered. The description adds real value beyond that by disclosing persistence scope and where the data surfaces downstream ('Aggregates are readable at feedback://insights'), which tells the agent its feedback is consumed, not fire-and-forget.

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 USE WHEN trigger, then a single dense sentence covering payload and follow-up location. The item-shape restatement is slightly redundant against the schema but is compact enough to justify its place; nothing else is wasted.

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?

An output schema exists and annotations cover the mutation profile, so the description needn't explain return values. It covers trigger, payload and downstream availability, leaving only minor gaps such as whether repeated submissions are deduplicated or rate-limited.

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 the baseline is 3. The description restates the item shape {category, severity, observation, suggested_action?, agent_confidence 0..1} and names agent identity and request_id, but this largely duplicates what the schema already documents and adds no new semantics such as value constraints or how request_id should be sourced.

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 — 'Persists structured feedback on a previous response' — and enumerates exactly what is stored (agent identity, request_id, items). No sibling tool covers feedback submission, so the agent can select it unambiguously from the description alone.

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

Usage Guidelines4/5

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

The leading 'USE WHEN something in a response was wrong, unclear or missing and you want to tell the operator' gives an explicit trigger condition. It stops short of stating when not to use it (e.g. don't submit duplicate feedback, don't use it for general questions), but no plausible sibling alternative exists to route against.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.