Skip to main content
Glama
Sign In

Swarm

by io.github.blackscaletech
OverviewDiscussionsAdmin

Get decision graph

swarm_get_decision_graph
Read-onlyIdempotent

Inspect the Space decision graph of Artifact links and evidence supporting learning candidates. Uses at most 64 recent Artifacts, 64 candidates and 128 Artifact edges, not full history. Page records with swarm_list_artifacts or swarm_list_learning_candidates. No promotion or recomputation.

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": "swarm_get_decision_graph"
  }
}

Input Schema

NameRequiredDescriptionDefault
space_idNoSpace ID from swarm_list_spaces; omit if sole.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / space_id / description
      Previous value: -"Omit for a single approved Space."New value: +"Space ID from swarm_list_spaces; omit if sole."
  2. Changed1 schema field changed
    • addedInput schema / properties / space_id / description
      Added value: +"Omit for a single approved Space."
  3. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes beyond them by disclosing the truncation window: at most 64 artifacts, 64 candidates, 128 edges, explicitly 'not full history'. That is the critical behavioral caveat for interpreting results. It does not say how the recent window is ordered or what happens when the space is larger than the caps.

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 short sentences, front-loaded with purpose, then limits, then alternatives. Every sentence earns its place and there is no boilerplate, though the middle sentence's numeric enumeration is dense.

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?

Output schema exists, so return values need not be explained, and the description covers scope, sampling bounds, alternatives, and non-mutation. What is missing is guidance on interpreting an incomplete graph (i.e. that absent edges may be due to the 64/128 caps rather than no evidence).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With a single optional parameter at 100% schema description coverage, the schema already explains space_id and its fallback when the caller belongs to a sole space. The description adds only the notion that the graph is scoped to a Space, which is consistent with but not richer than 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 resource: inspecting the 'Space decision graph of Artifact links and evidence supporting learning candidates'. That clearly separates it from sibling list tools like swarm_list_artifacts and swarm_list_learning_candidates, though 'decision graph' remains somewhat internal jargon an agent must interpret.

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?

Explicitly routes the agent to swarm_list_artifacts and swarm_list_learning_candidates for paging individual records, implying this tool is for the graph view rather than enumeration. It also sets a scope boundary with 'No promotion or recomputation', but never states a positive when-to-use condition (e.g. investigating why a candidate is supported).

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

All Swarm 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