Skip to main content
Glama
Sign In

Byteland

by dev.byteland
OverviewDiscussionsAdmin

A repository as a street

repo_street

Any public GitHub repository as a Byteland street: its top contributors (bots left out) with commit counts, who pushed in the last 30 days (their lights are on), who lives in Byteland, the total number of contributors, and the image and page links (street: an SVG for READMEs, page: the street page). total is null when GitHub will not list the contributors of a very large history; then the people are this month's committers.

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": {
      "owner": "<owner>"
    },
    "name": "repo_street"
  }
}

Input Schema

NameRequiredDescriptionDefault
repoNoRepository name. Leave it out for the owner’s skyline: their public repositories (no forks) by stars, lit when pushed in the last 30 days.
ownerYesRepository owner (user or organisation).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / repo / description
      Previous value: -"Repository name."New value: +"Repository name. Leave it out for the owner’s skyline: their public repositories (no forks) by stars, lit when pushed in the last 30 days."
    • changedInput schema / required
      Previous value: -[
-  "owner",
-  "repo"
-]New value: +[
+  "owner"
+]
  2. Added

TDQS

A3.5/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: bots are excluded from contributors, recency means pushed within 30 days, and the total is null when GitHub refuses to list contributors for very large histories, in which case the people returned are this month's committers. Not disclosed are auth requirements, rate limits, or how many contributors are returned.

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?

It is a single dense but front-loaded sentence that opens with the resource and then enumerates the returned fields, so nothing is buried. The metaphorical wording ('their lights are on', 'lives in Byteland') costs some clarity that plainer phrasing would have preserved.

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?

There is no output schema, and the description compensates by enumerating return fields (contributors with counts, recent pushers, total, image and page links) and the null-total edge case. For a two-parameter read tool this is nearly sufficient; only access requirements and result-size limits are absent.

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 description coverage is 100%, so the schema already explains both owner and repo, including the owner-only 'skyline' mode. The description adds context about what the results mean (commit counts, lights, link fields) but no new parameter-level semantics such as owner format or case sensitivity.

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?

It names a concrete verb and resource (public GitHub repository → its contributors, recent pushers, image/page links), so the agent knows exactly what data comes back. The framing as a 'Byteland street' and phrases like 'lives in Byteland' add metaphor that an agent must decode, and there is no explicit differentiation from siblings such as get_street or get_profile.

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?

The description says the tool works on 'any public GitHub repository', which bounds scope, but it never states when to choose this over get_street, get_stats, get_profile, or year_in_lights. There are no exclusions, prerequisites, or alternative-routing guidance.

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

All Byteland toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources