Skip to main content
Glama

ingest_reference

Ingests a reference codebase from a GitHub URL, local path, package registry, inline file map, or JS bundle into an indexed snapshot for minimal AST extraction and parity testing.

Instructions

Ingests a reference codebase from a GitHub URL, local directory, package spec (npm:/pypi:/cargo:), inline file map, or minified JS bundle into an indexed ReferenceSnapshot.

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": {
      "sourceUri": "<sourceUri>"
    },
    "name": "ingest_reference"
  }
}

Input Schema

NameRequiredDescriptionDefault
subpathNoOptional sparse subdirectory path.
sourceUriYesGitHub URL, local path, registry spec, or bundle identifier.
bundleCodeNoOptional minified JS/TS bundle code to normalize and ingest.
sourceKindNo
inlineFilesNo
bundleLanguageNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.3/5.0
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 key behavioral fact that this is a state-creating operation producing a persistent 'indexed ReferenceSnapshot', which tells the agent it is a mutation rather than a read. It says nothing about authentication for private GitHub sources, latency/cost of indexing, idempotency on re-ingest of the same URI, or size limits - all material for a networked ingest that writes an index.

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 front-loaded sentence that leads with the mutation verb and the target artifact, then enumerates the accepted source forms. Dense but every clause carries information; slightly heavy mid-sentence parenthetical enumeration, but no filler.

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 six-parameter, side-effecting tool with no annotations and no output schema, the definition covers what goes in and what artifact comes out, but leaves the agent guessing about return shape (snapshot ID?), async vs. synchronous behavior, re-ingest semantics, and failure modes. Adequate as an entry point, incomplete for reliable invocation.

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 only 50% across six parameters, so the description must compensate, and it does for the important ones: it reveals that sourceUri accepts registry spec syntax with npm:/pypi:/cargo: prefixes and 'inline file map' / 'minified JS bundle' variants, which map onto sourceKind's enum values, inlineFiles, and bundleCode/bundleLanguage beyond what the schema states. It omits 'subpath' (sparse subdirectory) entirely, leaving one parameter 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?

States a specific verb ('Ingests'), resource ('reference codebase'), an enumerated set of accepted source kinds, and names the produced artifact ('indexed ReferenceSnapshot'). The sibling tools (locate_feature_entrypoints, preview_graft_patch, etc.) are all downstream consumers of an indexed snapshot, so an agent can distinguish this as the ingestion/entry step, though the description never says so explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use or when-not-to-use guidance, no prerequisites, and no mention of alternatives or ordering relative to the sibling tools. The enumeration of source kinds implies the tool's input surface but gives no conditions for choosing it over any other step in the workflow.

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