Skip to main content
Glama
io.github.xngg1021/academic-research-kernel

io.github.xngg1021/academic-research-kernel

by xngg1021

academic_table_forensics

Audit AI/CS paper tables for partition conservation, constant-offset ablation regularity, and physical storage/bandwidth lower bounds to catch inconsistent or unsupported claims.

Instructions

Audit AI/CS paper tables for partition conservation, constant-offset ablation regularity, and physical storage/bandwidth lower bounds.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "academic_table_forensics"
  }
}

Input Schema

NameRequiredDescriptionDefault
partitionNo
ablation_tolNo
ablation_matrixNo
ablation_min_rowsNo
storage_bandwidthNo
ablation_baseline_colNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.8/5.0
Behavior2/5

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

No annotations exist, so the description carries the full burden, yet it never says whether this is read-only, what happens when a check block is omitted (all six parameters are optional), how failures are reported, or what tolerance defaults apply. It also does not disclose the output shape despite there being no output schema.

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?

A single front-loaded sentence naming the resource first and the checks second, with no filler. It is efficient, though the terseness is partly the cause of the missing detail noted elsewhere.

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 tool with a deeply nested six-parameter schema, no annotations, and no output schema, the description is substantially under-specified: an agent cannot tell which nested blocks to supply, what units the tolerances use, or what a result looks like. The one sentence does at least identify the three analytic domains the schema blocks correspond to.

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 six parameters with deep nesting, so the description must compensate. It only loosely maps its three check families onto the three nested objects; terms like tol, share_unit, share_tol_pct, ablation_min_rows, ablation_baseline_col, claims_full_system_storage, and min_metadata_overhead_bytes are given no meaning 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?

States a specific verb ('Audit') plus a specific resource ('AI/CS paper tables') and enumerates the three check families: partition conservation, constant-offset ablation regularity, and storage/bandwidth lower bounds. It is clear what the tool does, but nothing distinguishes it from siblings such as academic_check_percentage or academic_recompute_statistics.

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

Usage Guidelines2/5

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

There is no when-to-use guidance: no preconditions, no exclusions, and no mention of the alternative tools an agent should pick for overlapping checks (percentage verification, statistics recomputation). The agent must infer applicability entirely from the phrase 'AI/CS paper tables'.

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