Skip to main content
Glama
Sign In
Grove

Grove

by sai-softwareforest
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

grove_recommend_next

Read-only

Suggests the next project step by fixed priority—untested findings, code-matched declared gaps, then ready work items—with a short rationale and supporting IDs.

Instructions

Suggest one next step for a project by fixed priority, with a short rationale and the finding or work item ids behind it: map_untested findings first, then declared_untested findings whose words also appear in the code, then other declared_untested findings, then the oldest ready work item, then actual_undocumented findings. A deterministic heuristic; no model is called. 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_recommend_next"
  }
}

Input Schema

NameRequiredDescriptionDefault
projectYesProject name, or its numeric id.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already cover read-only, closed-world, and non-destructive behavior, and the description still adds real substance: deterministic ranking, no model invocation, and local-only execution with no data leaving to GitHub. What it does not say is what happens when no candidates exist or whether results are stable across calls.

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 is front-loaded, followed by the ranked priority list and then a compact behavioral note; each clause carries information. The priority chain is long but functional, and nothing reads as filler.

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 one-parameter, no-output-schema tool, the description covers return contents ('short rationale and the finding or work item ids') and the selection logic thoroughly. The only gap is edge-case behavior, such as an empty project or ties beyond the stated order.

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 the single 'project' parameter is already documented as a name or numeric id, so the description adds nothing parameter-specific. Baseline 3 applies when the schema carries the full burden.

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 description opens with a specific verb and resource ('Suggest one next step for a project') and then enumerates the exact priority tiers that drive the suggestion. This is distinguishable from siblings like grove_gaps or grove_work_list, which surface inventories rather than a single prioritized action.

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?

The triage intent is clear enough to imply when to call it, and 'A deterministic heuristic; no model is called' signals it needs no LLM-backed alternative. However, it never explicitly states when to prefer this over grove_gaps or grove_work_list, nor any preconditions (e.g., must a scan exist first).

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