Skip to main content
Glama
sqlite-graph-mcp

sqlite-graph-mcp

by developjik

Find orphans

graph_orphans

Identify dead code and stale docs by finding files with no inbound imports or links, plus symbols that are never exported; optionally include test and entry files.

Instructions

Operator 4 (minus) applied: files with no inbound imports/links (dead code, stale docs) and symbols that are never exported (dead-code candidates). Test and entry files are excluded unless asked for.

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_orphans"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
includeTestsNoInclude *.test.ts / *.spec.ts files.
includeEntriesNoInclude index/main/cli entry files.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It does disclose the important default filtering behavior (tests and entries excluded), which is genuinely useful. It stops short of stating that the operation is read-only, whether results are ordered/limited by default, or whether a stale index would skew results.

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

Conciseness3/5

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

Three compact sentences with no filler, and the core definition is front-loaded. The opening 'Operator 4 (minus) applied:' is a lead-in that costs tokens without helping an agent that has no operator taxonomy, and the sentence structure buries the exclusion rule at the end.

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 3-parameter read tool with no annotations and no output schema, the description covers what is found but not what is returned (file paths? symbol names? both in one list?) or whether indexing is a prerequisite. That leaves meaningful gaps for an agent trying to use the results downstream.

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 67%, and the description supplies the missing default semantics for the two boolean flags by saying tests and entries are excluded 'unless asked for' — the schema only says what the flags include, not that the default is off. The undocumented 'limit' parameter is not addressed, which keeps it below a 5.

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 the concrete result classes: files with no inbound imports/links and symbols never exported, with the parenthetical examples (dead code, stale docs) making the concept unambiguous. The leading 'Operator 4 (minus)' is opaque jargon that only makes sense against some external operator taxonomy, but the plain-language gloss immediately after it carries the meaning. It is distinguishable from graph_filter/graph_walk at a conceptual level, though not by explicit contrast.

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?

It states a real usage boundary: test and entry files are excluded unless requested, which tells the agent it must opt in via flags for those cases. However, it gives no guidance on when to prefer this over graph_filter or graph_walk, and no prerequisite such as whether the graph must be indexed first.

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