Skip to main content
Glama

save_triples

Saves extracted triples for one batch and marks its papers complete, including papers with no triples, then returns progress so extraction can continue.

Instructions

In-chat extraction, step 2: save the triples you extracted for one batch (each with paper_id, subject, subject_type, relation, object, object_type, evidence) and mark the batch's papers done, including papers with nothing to extract. Returns the progress message to show the user, e.g. "Saved 42 triples. 60 of 800 papers done (8%)".

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>",
      "paper_ids": "<paper_ids>",
      "triples": "<triples>"
    },
    "name": "save_triples"
  }
}

Input Schema

NameRequiredDescriptionDefault
run_idYes
triplesYes
paper_idsYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.16.1

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the full load and does disclose the key side effect: it marks the batch's papers as done, permanently advancing progress even for empty papers. It also tells the agent the return value is a user-facing progress message, which is actionable output context rather than a restatement of the 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 dense sentence followed by a concrete return-value example; the workflow role is front-loaded and the example earns its place by showing the progress format. The triple field list makes the sentence long but each item carries information.

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?

The output schema exists, so the return example is a bonus rather than a necessity, and the mutation and its edge case are covered. Gaps remain for a state-changing tool with no annotations: no mention of what happens on duplicate or re-saved batches, invalid paper_ids, or how triples must relate to the paper_ids argument.

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 coverage is 0%, so the description has to compensate, and it partially does by enumerating the expected triple keys (paper_id, subject, subject_type, relation, object, object_type, evidence). It says nothing about run_id, what paper_ids should contain relative to the triples, or the allowed values for the *_type and relation fields.

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 and resource (save the triples extracted for one batch) and situates it as 'step 2' of in-chat extraction, which separates it from the extraction step without naming that sibling. However, it never explicitly distinguishes itself from add_triples, which from the name alone could look interchangeable.

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?

'In-chat extraction, step 2' gives clear workflow context, and the instruction to mark papers done 'including papers with nothing to extract' is a concrete inclusion rule an agent would otherwise get wrong. It stops short of stating exclusions or naming when to prefer add_triples instead.

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