Skip to main content
Glama
Sign In
Grove

Grove

by sai-softwareforest
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

grove_gaps

Read-only

Lists a project's gap findings with pagination and counts by kind so you can review documentation, code, and test mismatches after a scan or map ingest.

Instructions

List a project's gap findings, paginated, with counts per kind. Kinds: declared_untested (docs state it, no test name overlaps), declared_unseen (docs state it, no code name overlaps), actual_undocumented (module never mentioned in docs), map_untested (an ingested map marks it untested). Every finding is a token-overlap heuristic to be checked by reading the code, not a verdict. Use after grove_scan or grove_ingest_map. 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_gaps"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoOnly findings of this kind, e.g. declared_untested.
limitNoPage size (default 50, max 200).
offsetNoNumber of items to skip.
projectYesProject name, or its numeric id.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already cover read-only and closed-world safety, yet the description adds a genuinely non-obvious caveat: every finding is a token-overlap heuristic, not a verdict, and must be checked against the code. It also reports result structure (counts per kind) and pagination. The 'local only, nothing sent to GitHub' sentence largely restates what readOnlyHint and openWorldHint=false already convey, so it is additive but not maximally so.

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?

Front-loaded with purpose, then the kind taxonomy, then prerequisite and caveat, then trust boundaries — a sensible order with no filler sentences. The closing privacy sentence duplicates the supplied annotations rather than adding new information, which is the one spot that does not fully earn its space.

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?

With no output schema, the description still conveys that results are paginated and include per-kind counts, and it explains what each finding kind means. Combined with 100% schema coverage and safety annotations, an agent has enough to call this correctly and interpret results; only the exact response envelope and count field names remain unspecified.

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 100%, so baseline would be 3, but the description adds real meaning the schema lacks: the schema types 'kind' as a bare string with only an example, and the description supplies the authoritative enumeration of all four kinds plus their semantics. Limit/offset/project are left entirely to the schema, which is acceptable given full coverage.

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?

States a specific verb and resource ('List a project's gap findings') plus the shape of the result ('paginated, with counts per kind'). It also enumerates the four kinds with one-line definitions, so an agent can tell this apart from the producing siblings grove_scan and grove_ingest_map without opening any schema.

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?

'Use after grove_scan or grove_ingest_map' gives explicit sequencing and identifies the prerequisite producers. It also warns that findings are heuristics requiring code verification, which shapes how results should be consumed. It does not state when not to use it or name a competing consumer tool, so it falls short of a full 5.

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