Skip to main content
Glama

Get investigation

refix_get_investigation
Read-onlyIdempotent

Read the state of an investigation started with refix_investigate. While it is queued or running, this call waits up to 25 seconds for the state to change or for a new step in progress, so call it again right away until it finishes. The user sees nothing while this runs unless you send it: when a result has new_steps, tell the user in one short plain sentence what Refix is doing before the next call. Use Refix's numbers exactly. Never starts or reruns analysis. When the state is needs_input, ask the user pending_input.question and send their answer with refix_investigate and response_to_input_id. When the answer ends with suggested follow-ups, offer them to the user; send the one they pick with refix_investigate and this session_id.

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": {
      "investigation_id": "<investigation_id>"
    },
    "name": "refix_get_investigation"
  }
}

Input Schema

NameRequiredDescriptionDefault
investigation_idYes

Output Schema

NameRequiredDescriptionDefault
stateYes
answerYes
questionYes
new_stepsYesRaw notes on what Refix did since your previous call, oldest first. Empty when nothing is new. Not text for the user: say it in your own words.
error_codeYes
report_urlYes
session_idYes
next_actionYesWhat to do before the next call, when set.
pending_inputYes
investigation_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • removedOutput schema / properties / latest_step
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "type": "string"
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ],
      -  "description": "The newest step, ready to send to the user. Null when nothing is new."
      -}
    • changedOutput schema / properties / new_steps / description
      Previous value: -"What Refix did since your previous call, oldest first. Empty when nothing is new."New value: +"Raw notes on what Refix did since your previous call, oldest first. Empty when nothing is new. Not text for the user: say it in your own words."
    • changedOutput schema / required
      Previous value: -[
      -  "investigation_id",
      -  "session_id",
      -  "state",
      -  "question",
      -  "pending_input",
      -  "answer",
      -  "error_code",
      -  "new_steps",
      -  "latest_step",
      -  "next_action",
      -  "report_url"
      -]New value: +[
      +  "investigation_id",
      +  "session_id",
      +  "state",
      +  "question",
      +  "pending_input",
      +  "answer",
      +  "error_code",
      +  "new_steps",
      +  "next_action",
      +  "report_url"
      +]
  2. Changed5 schema fields changed
    • addedOutput schema / properties / latest_step
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "The newest step, ready to send to the user. Null when nothing is new."
      +}
    • addedOutput schema / properties / new_steps
      Added value: +{
      +  "description": "What Refix did since your previous call, oldest first. Empty when nothing is new.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • addedOutput schema / properties / next_action
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "description": "What to do before the next call, when set."
      +}
    • removedOutput schema / properties / progress
      Removed value: -{
      -  "description": "What Refix has done so far in this run, oldest first. Tell the user each new step. Empty once the run is completed.",
      -  "items": {
      -    "type": "string"
      -  },
      -  "type": "array"
      -}
    • changedOutput schema / required
      Previous value: -[
      -  "investigation_id",
      -  "session_id",
      -  "state",
      -  "question",
      -  "pending_input",
      -  "answer",
      -  "error_code",
      -  "progress",
      -  "report_url"
      -]New value: +[
      +  "investigation_id",
      +  "session_id",
      +  "state",
      +  "question",
      +  "pending_input",
      +  "answer",
      +  "error_code",
      +  "new_steps",
      +  "latest_step",
      +  "next_action",
      +  "report_url"
      +]
  3. Changed2 schema fields changed
    • addedOutput schema / properties / progress
      Added value: +{
      +  "description": "What Refix has done so far in this run, oldest first. Tell the user each new step. Empty once the run is completed.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
    • changedOutput schema / required
      Previous value: -[
      -  "investigation_id",
      -  "session_id",
      -  "state",
      -  "question",
      -  "pending_input",
      -  "answer",
      -  "error_code",
      -  "report_url"
      -]New value: +[
      +  "investigation_id",
      +  "session_id",
      +  "state",
      +  "question",
      +  "pending_input",
      +  "answer",
      +  "error_code",
      +  "progress",
      +  "report_url"
      +]
  4. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description goes well beyond them by disclosing the long-poll behavior (up to 25 seconds, returns early on state change or new step), the state machine (queued/running/needs_input/finished), and the surprising requirement that the user sees nothing unless the agent narrates new_steps. That user-facing narration rule is non-obvious behavior an agent could not infer from any structured field.

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?

Purpose and polling behavior are front-loaded, then conditional branches (needs_input, follow-ups) follow in the order an agent will encounter them. Sentences are long and densely packed with state-specific instructions, but each one carries an actionable rule rather than 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 return values need no explanation, yet the description still flags the key fields an agent must act on (new_steps, pending_input.question, suggested follow-ups). For a single-parameter polling tool the description covers the full call loop, the terminal conditions, and the user-facing obligations, with nothing material 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?

With schema coverage at 0% for the single required parameter, the description has to carry the meaning of investigation_id; it implies the value by tying the tool to "an investigation started with refix_investigate," which is enough to know where the id comes from. However it never explicitly defines the parameter, and it refers to "this session_id" for the follow-up flow, a name that does not match the schema's investigation_id, leaving a small ambiguity about whether the same value is reused.

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?

Starts with a specific verb and resource ("Read the state of an investigation") and immediately ties it to the sibling that creates it ("started with refix_investigate"). It also rules out the adjacent action with "Never starts or reruns analysis," so an agent can distinguish it from refix_investigate without inspecting 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 explicit operating loop: call again right away while queued/running, and stop polling only when finished. It names the alternative and the exact routing for the two edge states — needs_input goes to refix_investigate with pending_input.question and response_to_input_id, and suggested follow-ups go back via refix_investigate with the session_id.

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.

Resources