Skip to main content
Glama
Sign In

Krusgraph

by com.krusgraph
OverviewDiscussions(1)Admin

Start Krusgraph: a guided path (experimental)

start
Read-onlyIdempotent

A guided path for a first or vague message ('start', 'start Krusgraph', 'help', 'what can you do', 'check my data'): workspace, source, schema, map, check, decide, doubled totals, a dry run of all builds with the data flow, then create after a second confirmation of the names. Returns JSON {step, path, actions: [{tool, arguments, say}], after}: each action is an existing tool; after is the next start call. Changes nothing. Errors: {error, kind, hint}.

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": "start"
  }
}

Input Schema

NameRequiredDescriptionDefault
planNo{keys, confirmed, decisions} so far, as review_plan takes them.
stepNoStep to show: map, check, decide, totals, dry_run or create (the answer's after names it).
createNoStep create: dry-run item names the user asked to create.
sampleNotrue: the synthetic shop sample; no Fabric.
schemaNoChosen so far; "" if not yet.
sourceNoChosen so far; "" if not yet.
confirmNoStep create: true only after the user said yes to exactly those names.
workspaceNoChosen so far; "" if not yet.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior5/5

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

'Changes nothing' is consistent with readOnlyHint=true and destructiveHint=false, and it reinforces rather than contradicts the annotations. Beyond that it discloses the return contract ({step, path, actions, after}), explains that each action is an existing tool plus the arguments and text to use, that `after` is the next start call, and gives the error shape {error, kind, hint}. It also flags that create requires a second confirmation of the names, which is real behavioral context not present in the annotations.

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?

The structure is sensible: purpose and triggers first, then return value, then the no-side-effect guarantee, then errors. It is compact with no filler, though the opening sentence is a long run-on stuffed with step names and phrases like 'doubled totals' that are not explained and slow comprehension.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an eight-parameter orchestration tool with no output schema, the description covers everything an agent needs: when to call it, what the response object contains, how to continue via `after`, that nothing is mutated, and what errors look like. The remaining ambiguity is only in the names of intermediate steps, which the returned `actions` array resolves at runtime.

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 eight parameters are already documented, including the plan, step enum-ish values, create, confirm, sample, and the 'chosen so far' fields. The description adds meaning only for `confirm` ('second confirmation of the names') and for the step sequence; it does not explain plan shape, sample behavior, or how empty-string placeholders should be handled. Baseline 3 is appropriate.

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?

The description names a specific role: the guided entry point for a first or vague message, listing the exact phrases that trigger it ('start', 'help', 'what can you do', 'check my data'). It implicitly separates itself from the many action siblings by being the orchestration dispatcher rather than an executor. The step vocabulary ('map, check, decide, doubled totals') is jargon that only makes sense once you know the siblings, which keeps it from a 5.

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?

It gives explicit trigger conditions (first or vague user message) with concrete example utterances, which is strong when-to-use guidance. It does not state when NOT to use it — e.g. that a concrete request should go straight to the specific sibling tool instead of through the path — so the agent must infer the exclusion.

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

All Krusgraph 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