Skip to main content
Glama
sqlite-graph-mcp

sqlite-graph-mcp

by developjik

Filter a node set

graph_filter

Filter explicit node IDs by kind, path glob/prefix/suffix, name, tag, or regex to narrow graph_find results for targeted graph traversal or analysis.

Instructions

Operator 3 (filter): narrow an explicit node set by kind, path glob/prefix/suffix, name, or tag (tags include code, doc, test, entry, manifest, exported). Combine with graph_find output ids.

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": {
      "ids": "<ids>"
    },
    "name": "graph_filter"
  }
}

Input Schema

NameRequiredDescriptionDefault
idsYesNode ids to filter.
tagNo
kindNo
nameNoCase-insensitive substring of the node name.
pathNoGlob, e.g. src/**/*.ts
limitNo
regexNoJavaScript regex over the node name.
prefixNo
suffixNo
notKindNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations, the description carries the full behavioral burden; it does signal a read-only narrowing operation and usefully discloses the tag vocabulary (code, doc, test, entry, manifest, exported) that the schema leaves undocumented. It does not say how multiple filters combine (AND vs OR), whether an empty result is returned as an empty list or an error, or what the default limit is.

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 with the operator role front-loaded, followed by one short chaining hint. Every clause carries filter information; there is no filler, though the enumeration is packed tightly enough to be slightly hard to parse.

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?

For a 10-parameter tool with no annotations and no output schema, the description covers roughly half the surface: the main filter fields plus tag values. Missing coverage of regex, limit, and notKind leaves an agent guessing on three parameters that materially affect results.

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 only 40% across 10 parameters, so the description needs to compensate. It adds meaning for tag (vocabulary), path ("glob, e.g. src/**/*.ts"), and name, and groups prefix/suffix under path, but says nothing about regex, limit, or notKind, which are undocumented in both places.

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?

"Operator 3 (filter): narrow an explicit node set" gives a specific verb plus resource and enumerates the filter dimensions (kind, path, name, tag), so an agent knows exactly what the tool does. It also implicitly distinguishes itself from graph_find by taking ids as input rather than producing them, though it never names the sibling explicitly.

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?

"Combine with graph_find output ids" tells the agent this is a chained/second-stage operation and where its input comes from, which is real usage context. It stops short of stating when not to use it (e.g., when ids are unknown) or what the alternatives are for open-ended searching.

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