Skip to main content
Glama

extract_triples

Extracts methods, data, theories, constructs, settings, and findings from paper titles and abstracts in a run, batch by batch, adding structured triples and resuming cached progress.

Instructions

Extract triples (methods, data, theories, constructs, settings, findings) from the titles and abstracts of a run with "claude-code", "codex", "anthropic" or "openai" (see triple_extraction_options), batch by batch, and add them to the run. Reports progress after every batch; answers are cached, so a repeated or interrupted run resumes. Large corpora take a while: tell the user the number of papers first, or test with max_papers=30.

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": {
      "run_id": "<run_id>"
    },
    "name": "extract_triples"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNo
run_idYes
backendNoclaude-code
batch_sizeNo
max_papersNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.16.1

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses batching behavior, per-batch progress reporting, caching so interrupted or repeated runs resume, and that large corpora are slow. It does not cover failure modes, whether partial batches persist, or duplicate handling, leaving some behavioral gaps.

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?

Front-loads the verb and resource, then layers operational facts in a single dense paragraph with no filler sentences. The parenthetical field enumeration and cross-reference are dense but each clause carries real information; slightly long, yet nothing is clearly redundant.

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?

An output schema exists, so return values need not be described, and the description covers the remaining high-value facts: cost/time expectations, caching/resume semantics, and pre-run user communication. The main shortfall is parameter-level clarity for model vs backend given 0% schema coverage.

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 5 parameters, so the description must compensate. It names the accepted backend values ('claude-code', 'codex', 'anthropic', 'openai'), implies run_id ('of a run') and batch_size ('batch by batch'), and explains max_papers via the 30-paper test suggestion, but never distinguishes model from backend or says what batch_size defaults to, leaving ambiguity on the most confusable parameter pair.

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

Purpose5/5

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

States a specific verb+resource ('Extract triples from titles and abstracts of a run') and enumerates exactly what a triple contains (methods, data, theories, constructs, settings, findings). It also clarifies that extraction happens batch by batch and results are added to the run, which distinguishes it from siblings like add_triples or next_triple_batch.

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?

Gives concrete operational guidance: consult triple_extraction_options for backend/model choice, test with max_papers=30 first, and tell the user the paper count before launching a large corpus. It stops short of stating when to avoid this tool in favor of add_triples or next_triple_batch, so it is strong but not fully exhaustive on alternatives.

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