Skip to main content
Glama
sqlite-graph-mcp

sqlite-graph-mcp

by developjik

Walk the graph

graph_walk

Traverse code graph edges from selected nodes to trace dependencies, definitions, dependents, or references, returning traversal depth and file:line citations for each result.

Instructions

Operator 2 (walk): traverse edges from a set of nodes with a recursive CTE (cycle-safe, depth capped). Direction out = dependencies/definitions, in = dependents/references. Each node returns its traversal depth and a path:line citation.

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": {
      "start": "<start>"
    },
    "name": "graph_walk"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
startYesNode ids or keys, as returned by graph_find.
edgeTypeNoEdge types to follow. Defaults to all.
maxDepthNoDefault 6.
directionNoDefault "out".

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
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 disclose real behavior beyond the schema: the traversal is cycle-safe, depth-capped, and returns both a depth value and a path:line citation per node. It stops short of describing what happens when limit is hit, whether results are truncated or ordered, or the cost of walking a high-degree node.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the walk operation and its mechanism, then direction semantics, then return shape. Every clause carries information an agent needs; nothing is restated from the schema verbatim.

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?

For a 5-parameter traversal tool with no output schema and no annotations, the description covers the essentials: mechanism, safety properties, direction meaning, and the shape of each returned node. The remaining gap is limit/truncation behavior, which is the one thing an agent could still get wrong.

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?

Schema coverage is 80%, so the baseline is 3, and the description earns above that by clarifying direction semantics that the schema only labels ('Default "out"'), explaining that 'out' follows dependencies/definitions while 'in' follows dependents/references. It adds no detail on limit or edgeType behavior, but those are already documented in the schema.

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 and resource — 'traverse edges from a set of nodes' — and pins the mechanism ('recursive CTE, cycle-safe, depth capped'). The 'Operator 2 (walk)' framing plus the reference to graph_find for node ids lets an agent tell this apart from graph_find/graph_filter without opening another schema.

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 clear operating context: use it to walk edges from a starting set, with direction semantics spelled out (out = dependencies/definitions, in = dependents/references), which tells the agent which mode fits a given question. It does not explicitly state when to prefer a sibling such as graph_filter over a walk, so the exclusion is implied rather than stated.

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