Skip to main content
Glama
crisp-plugin-mcp

crisp-plugin-mcp

by amitray007

report_feedback_missing_tool

Reports feedback to the Crisp team about missing or broken MCP server functionality when an AI agent gets stuck, using a provided action trace.

Instructions

Reports feedback to the Crisp team about something missing or broken on this MCP server. This tool should be suggested to the user if the AI agent gets stuck. An action_trace should be provided.

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_trace": "<action_trace>"
    },
    "name": "report_feedback_missing_tool"
  }
}

Input Schema

NameRequiredDescriptionDefault
action_traceYesA short trace of the decision chain that was executed, provided by the LLM and not the user. This should not include any private information from the session, as this is shared with Crisp team.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.2

TDQS

A3.8/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose the important trait that data leaves the session and is shared with the Crisp team. However it omits whether user consent is required before sending, whether a ticket/confirmation is returned, and whether calls are rate-limited or logged, so the behavioral picture remains partial for an outbound-reporting tool.

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?

Three short sentences, front-loaded with purpose, then the usage trigger, then the parameter expectation. No redundant or filler wording.

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 one-parameter reporting tool with no output schema, the definition covers purpose, trigger, and the key privacy constraint. What is missing is what the agent should do after calling it (inform the user, continue, stop), which would make it fully self-sufficient.

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?

There is a single parameter and schema coverage is 100%, including the privacy warning in the schema itself, so the baseline is 3. The sentence 'An action_trace should be provided' merely restates the required field without adding format or content guidance (e.g. what granularity of decision chain is useful).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: reporting feedback about something missing or broken on this MCP server, directed at the Crisp team. It is unambiguously a meta/diagnostic tool, clearly distinct from every sibling (which all operate on conversations, people, helpdesk, or websites). It stops short of a 5 because it never explicitly frames itself against other escalation paths.

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?

It gives a concrete trigger condition — suggest this tool to the user when the agent gets stuck — which is exactly the decision point an agent needs. It does not state when *not* to use it (e.g. for recoverable errors or user-facing questions), so there is a modest gap.

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