Skip to main content
Glama
rupturetrace-mcp

rupturetrace-mcp

by Susan571

assess_claims_batch

Assess multiple scientific claims sequentially, save a verifiable run directory, and return a run summary plus one compact row per completed claim.

Instructions

Run many claims sequentially and write a complete, verifiable run directory to out_dir.

Provide either input_path (JSONL rows with claim and optional problem_id / problem_version) or a list of claim strings. Returns the run summary plus one compact row per completed claim.

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": {
      "out_dir": "<out_dir>"
    },
    "name": "assess_claims_batch"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
modelNo
claimsNo
backendNohttp
key_envNo
out_dirYes
timeoutNo
api_modeNochat
endpointNo
json_modeNo
overwriteNo
input_pathNo
web_searchNo
qwen_hostingNodashscope
with_h1_ablationNo
continue_on_errorNo
allow_source_fetchNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.1/5.0
Behavior2/5

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

With no annotations, the description carries the full behavioral burden, and it does disclose that execution is sequential, that a run directory is written, and that the return is a summary plus one row per completed claim. However, for a 17-parameter tool it says nothing about overwrite semantics (default false — what happens if out_dir already exists?), continue_on_error behavior, authentication via key_env, timeouts, or backend-dependent requirements.

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?

The write-and-return contract is front-loaded in the first sentence, followed by the input options and output shape. Three sentences with little waste, though the stray line breaks and the parenthetical JSONL clause make it slightly denser than needed.

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

Completeness2/5

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

There is no output schema, and the description does sketch the return value, which helps. But for a batch execution tool with 17 parameters, zero annotations, and no output schema, the omissions around overwrite/error handling and parameter meanings leave an agent unable to call it safely without reading the schema.

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 0% across 17 parameters, so the description must compensate, and it only partially does. It adds genuinely useful meaning for input_path (JSONL rows containing claim and optional problem_id/problem_version — fields not visible in the schema at all) and clarifies out_dir's role, but the remaining ~13 parameters (model, backend, api_mode, key_env, timeout, overwrite, web_search, qwen_hosting, with_h1_ablation, limit, json_mode) get no explanation anywhere.

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 opens with a specific verb and resource ('Run many claims sequentially') and adds a concrete side effect ('write a complete, verifiable run directory to out_dir'). The plural 'many claims' plus the tool name distinguishes it from the single-claim sibling assess_claim, though the sibling is never 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?

It usefully states the two mutually exclusive input modes (input_path vs. a list of claim strings) and the JSONL row shape, which is real usage guidance. It never says when to pick this tool over assess_claim or when to prefer file input over an inline list, and gives no prerequisites for the model/backend parameters.

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