Skip to main content
Glama

Veyrul media knowledge hub

Assisted investigation (unavailable)

start_investigation
Idempotent

New assisted investigations are currently unavailable. Retrieve saved knowledge or create an ordinary public community question. Existing investigation history, exact submission replay and cancellation remain supported under their original permissions.

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": {
      "input": "<input>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "start_investigation"
  }
}

Input Schema

NameRequiredDescriptionDefault
inputYes
idempotency_keyYesRequired. Retry this exact mapped REST request with the same key for 24 hours; no duplicate work.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

B3.2/5.0
Behavior3/5

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

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=true and idempotentHint=true, so the safety profile is already carried structurally. The description adds useful permission context ('remain supported under their original permissions'), but it does not say what an actual call would return now — a hard error, a refunded no-op, or a successful replay keyed on idempotency_key — which is the single most important behavior for a deprecated mutation endpoint.

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?

Three short sentences with the most important fact (unavailability) front-loaded, followed by alternatives and the supported carve-outs. No filler, though the middle sentence packs two different alternatives together slightly awkwardly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a deprecated endpoint the notice covers alternatives and surviving capabilities, which is the core need. It omits the return behavior on invocation and never states plainly 'do not call this for new questions', so an agent still has to infer whether the tool is callable at all.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

At 50% schema coverage, the description needs to compensate and it adds nothing: no mention of the required title/question, the record_refs cap of 8, the pinned anthropic-only guide_permission, or the idempotency_key replay window. The nested `input` object carries most of the complexity and is entirely undocumented outside the raw schema.

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

Purpose3/5

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

The description never says what an assisted investigation actually does (it is a deprecation notice, not a purpose statement), but it does clearly communicate the operative fact: new assisted investigations are unavailable. The resource is named and the state is unambiguous, so an agent can tell it should not be used for new work.

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 explicitly redirects to two alternatives (retrieve saved knowledge, or create an ordinary public community question) and carves out the still-supported paths: existing investigation history, exact submission replay, and cancellation. It stops short of naming the sibling tools (get_investigation, cancel_investigation) that implement those paths, leaving the agent to infer them from the tool list.

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