Skip to main content
Glama
xiaweiyi713

CiteGuard

by xiaweiyi713
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

audit_claim_support_tool

Audit many claim-citation pairs in one batch, identify unsupported claims, and produce risk-ranked reports with suggested fixes for review.

Instructions

Judge MANY claim-citation support pairs at once.

items is a list of objects with a required claim plus any citation fields accepted by verify_citation_tool: raw_text, title, authors, year, venue, doi, arxiv_id, full_text, full_text_file, and optional per-item lang. An item may alternatively provide citations, a non-empty list of citation objects, to assess whether a claim is supported by the cited set. Returns a per-item support report plus summary, risk_ranking, and review_summary. Agents should branch on review_summary.triage_plan, compact risk_reason, and suggested_fix.kind / suggested_fix.requires_user_confirmation instead of parsing support prose or silently editing citations. review_summary.suggested_fix_summary.auto_apply_allowed=false means batch repairs must be proposed to the user, not silently applied. Items may include lawful caller-provided full_text excerpts or full_text_file paths; those are tagged as evidence_scope=full_text, and CiteGuard will not fetch gated full text. Set high_risk_only=true to return only high-risk rows while preserving full-batch review_summary counts and filtered.returned_indexes / filtered.omitted_indexes for original-input traceability.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
langNo
itemsYes
max_workersNo
high_risk_onlyNo
counterevidence_top_kNo
include_counterevidenceNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.3

TDQS

A3.9/5.0
Behavior5/5

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 delivers: it names the return components, instructs agents to branch on triage_plan and suggested_fix, warns against silently editing citations, explains auto_apply_allowed=false, describes evidence_scope=full_text behavior, and clarifies high_risk_only preservation. This is strong, actionable transparency.

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 description is front-loaded and dense with useful operational details, and every sentence contributes information. It loses a point because the paragraphs are long and the structure could be improved with bullets or shorter scannable sentences.

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 complex tool with no output schema and no annotations, the description covers invocation, input shape, output routing, and filtering behavior well. Gaps remain around counterevidence-related parameters and explicit sibling selection, but the core guidance is sufficient for correct basic use.

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?

The description gives detailed semantics for `items` and `high_risk_only`, which is valuable given 0% schema coverage. However, three parameters (`max_workers`, `counterevidence_top_k`, `include_counterevidence`) are not explained, and the top-level `lang` parameter is not clearly distinguished from the per-item `lang`. Compensation is partial.

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: 'Judge MANY claim-citation support pairs at once.' It clearly conveys batch action on claim-citation pairs, but it does not explicitly differentiate the tool from siblings such as check_claim_support_set_tool or verify_citation_tool, so it stops short of full sibling differentiation.

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 'at once' phrasing implies this tool is for batch assessment, and the description gives substantial guidance on constructing items and handling output. However, it never explicitly says when to choose this tool over alternatives or provides exclusions, leaving some selection reasoning to inference.

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

Deploy Server

Other Tools