Skip to main content
Glama
rupturetrace-mcp

rupturetrace-mcp

by Susan571

assess_claim

Run the full RuptureTrace pipeline on one scientific claim to get rubric labels, the selected evidence relation, top relation scores, and rationales, with optional artifact output.

Instructions

Run the full RuptureTrace pipeline on one claim using a configured model backend (7 model calls; 9 with ablation).

model/endpoint default to the TA2_MODEL / TA2_ENDPOINT environment variables; the API key is read from the environment variable named by key_env (default OPENAI_API_KEY for http, DASHSCOPE_API_KEY for qwen) and is never passed as an argument. If out_dir is given, the complete verifiable artifact directory is written there. Returns a summary (labels, selected relation, top relation scores, rationales).

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": {
      "claim": "<claim>"
    },
    "name": "assess_claim"
  }
}

Input Schema

NameRequiredDescriptionDefault
claimYes
modelNo
backendNohttp
key_envNo
out_dirNo
timeoutNo
api_modeNochat
endpointNo
json_modeNo
overwriteNo
web_searchNo
qwen_hostingNodashscope
with_h1_ablationNo
allow_source_fetchNo
include_full_recordNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
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 valuable traits: the call cost (7 model calls, 9 with ablation), that the API key is read from the environment and never passed as an argument, and that out_dir causes an artifact directory to be written. It says nothing about overwrite behavior, timeout effects, whether web_search/allow_source_fetch make external network calls, or failure modes.

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 compact sentences, front-loaded with the pipeline and call-count cost signal before the environment/IO details. Dense but no filler; the parenthetical call count earns its place as a cost signal.

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?

It correctly summarizes the return value (labels, selected relation, top scores, rationales), which is needed since there is no output schema, and it explains the auth/env model. However, for a 15-parameter tool with zero annotation coverage, the undocumented configuration knobs leave an agent unable to choose values confidently.

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?

Schema description coverage is 0% across 15 parameters, so the description must compensate and it only covers four of them (model, endpoint, key_env, out_dir). The eleven remaining parameters — backend, timeout, api_mode, json_mode, overwrite, web_search, qwen_hosting, with_h1_ablation, allow_source_fetch, include_full_record — receive no meaning beyond their bare names and defaults.

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?

"Run the full RuptureTrace pipeline on one claim using a configured model backend" gives a concrete verb, resource, and scope. The phrase "one claim" implicitly separates it from the sibling assess_claims_batch, though no sibling is named explicitly.

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

Usage Guidelines3/5

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

The description establishes prerequisites (configured model backend, env vars for model/endpoint/key) and what out_dir triggers, which implies when the tool is applicable. It never states when to prefer this over assess_claims_batch or the host-round tools, nor any exclusion conditions.

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