Skip to main content
Glama
Sign In
Grove

Grove

by sai-softwareforest
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

grove_scan

Scans a project root to rebuild its declared, actual, and test blueprint layers and recompute gap findings after code or docs change. Read-only and deterministic; honors .gitignore and scan caps.

Instructions

Scan a project's root directory and rebuild its blueprint (declared / actual / tests layers), then recompute gap findings. Use after creating a project and whenever the code or docs have changed. The scan is deterministic and read-only: it never writes inside the project, honours .gitignore, and stops at the file and time caps (reported in the result). Returns counts per layer and per finding kind plus a small sample; page the rest with grove_gaps and grove_blueprint_get. It replaces earlier scan-derived items and findings but keeps knowledge, work items and map-ingested items. 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>"
    },
    "name": "grove_scan"
  }
}

Input Schema

NameRequiredDescriptionDefault
projectYesProject name, or its numeric id.
max_filesNoFile cap for this scan (default 4000).
max_secondsNoTime cap in seconds (default 8).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior2/5

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

The description openly discloses the most important traits beyond the schema – determinism, .gitignore honouring, file/time caps, and that it replaces earlier scan-derived items while keeping knowledge, work items and map-ingested items. However, it labels the operation 'read-only' while annotations declare readOnlyHint=false and the body describes replacing existing items, so the framing conflicts with the structured safety metadata.

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?

Purpose, usage, and constraints are front-loaded in the opening sentences and the trailing 'local only' note is a clarifying addition rather than filler. It runs a bit long for three parameters, but each sentence carries information.

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 mutating, no-output-schema tool, the description covers return shape ('counts per layer and per finding kind plus a small sample'), pagination routing, caps, and what is preserved versus replaced. The one substantive gap is the inconsistent read-only claim, which undercuts the otherwise complete behavioral picture.

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 optional caps carry defaults and meanings in the schema, so the description can add little. It does frame them as caps whose values are 'reported in the result', which is mildly useful context but not new syntax or format detail.

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?

The first sentence gives a specific verb and resource plus the exact scope: 'Scan a project's root directory and rebuild its blueprint (declared / actual / tests layers), then recompute gap findings.' That distinguishes it cleanly from grove_blueprint_get and grove_gaps, which only read.

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

Usage Guidelines5/5

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

It names the triggering conditions explicitly ('after creating a project and whenever the code or docs have changed') and tells the agent where to go instead for full results ('page the rest with grove_gaps and grove_blueprint_get'). No inference is needed to choose between this and the read siblings.

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