Skip to main content
Glama
Sign In
Grove

Grove

by sai-softwareforest
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

grove_ingest_map

Ingest a markdown architecture map into a project to store its text as a knowledge document and seed declared, code-observed, and untested items; re-ingesting replaces prior seeded content.

Instructions

Ingest a markdown architecture map (for example a MAP.md) into a project. The file is only read, never modified. Its full text is stored as a knowledge document (key from the file name; a new revision each time), and blocks carrying the evidence labels documented / observed-in-code / untested seed declared items, actual items and map_untested findings. Use when a human or agent has written a map of the codebase. Re-ingesting replaces what the same map seeded before. Grove is local only: scans are read-only and nothing is sent to GitHub or any other service.

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": {
      "project": "<project>",
      "path": "<path>"
    },
    "name": "grove_ingest_map"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesPath to the markdown file on this machine.
projectYesProject name, or its numeric id.

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?

Adds real value beyond the annotations: the source file is read-only, full text is persisted as a knowledge document with a revision per ingest, and prior seeds from the same map are replaced. However, the closing sentence about 'scans are read-only' describes a different operation and slightly muddies what this tool actually writes; it also doesn't say whether replacement is recoverable or what a failure mid-ingest leaves behind. Since destructiveHint=false and readOnlyHint=false are already declared, this is decent but not rich.

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?

Front-loaded with the action, but the third sentence packs document storage, revision behavior, and three evidence labels into one dense clause that is hard to parse on a first read. Content earns its place; the phrasing does not.

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?

Covers the mutation semantics (what is stored, what gets replaced), the read-only treatment of the source file, and the local-only/no-external-service boundary. With no output schema, the description reasonably does not need to explain return values.

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 100% and both parameters are documented in the schema, so baseline 3 applies. The description adds only a little: that the knowledge document key derives from the file name, implying path is used both for reading and naming.

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?

Names a specific verb+resource: 'Ingest a markdown architecture map (for example a MAP.md) into a project', and clarifies the downstream effect (stored as a knowledge document, seeds map items). It is distinguishable from grove_knowledge_write and grove_scan by the map-specific evidence labels, though it never explicitly contrasts itself with those siblings.

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 a clear trigger: 'Use when a human or agent has written a map of the codebase', plus the important re-run condition 'Re-ingesting replaces what the same map seeded before'. It stops short of naming an alternative tool or stating when not to use it.

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

Deploy Server

Other Tools