Skip to main content
Glama
Sign In

Spaces by Peakflo

by ai.peakflo
OverviewDiscussionsAdmin

graph_generate

Generate entities and relationships from datastore documents using AI, with automatic linkage back to source documents. Scans tenant datastores for content, proposes entities/relationships, and links each to its source document for provenance. Use apply=false for a dry-run preview.

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": "graph_generate"
  }
}

Input Schema

NameRequiredDescriptionDefault
fullNoWhether to run a full scan (default true). Set false for incremental scan since last run.
applyNoWhether to persist generated entities (default true). Set false for dry-run preview.
focusNoOptional focus area to guide generation (e.g. "vendor relationships", "payment terms")
modelNoOptional LLM model override

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already flag this as non-read-only but non-destructive; the description usefully adds the provenance behavior (entities linked to source documents) and the dry-run escape hatch. It does not disclose what happens on re-runs (duplication vs. update), whether large LLM scans are slow or costly, or how many entities may be created.

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?

Three sentences, front-loaded with the core action and output, then provenance, then the dry-run hint. The second sentence partially restates the first ('proposes entities/relationships' after 'generate entities and relationships'), but overall it is tight.

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?

It conveys what the tool produces and how to preview it safely, which is the core need. For a write-capable tool with no output schema, it omits re-run/idempotency behavior and any prerequisite about linked datastores, leaving meaningful gaps.

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 100%, so all four parameters are already documented, and the description only restates the apply=false dry-run semantics. It adds no meaning for 'full', 'focus', or 'model' beyond the schema.

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 output ('Generate entities and relationships') plus the source ('datastore documents') and a distinctive trait ('automatic linkage back to source documents'). That separates it from graph_create_entity_type, graph_link_datastore, and graph_entities without naming them. It stops short of explicitly contrasting with those siblings.

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?

Only one usage instruction is given: 'Use apply=false for a dry-run preview.' There is no guidance on when to choose this over graph_link_datastore or incremental runs, and no stated prerequisite (e.g. that a datastore must first be linked) even though the tool scans 'tenant datastores'.

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

All Spaces by Peakflo toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources