Skip to main content
Glama
costajohnt

oss-autopilot

by costajohnt
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Hybrid

daily

Monitor and prioritize open pull requests by fetching CI status, reviews, and conflict data for efficient daily review workflows.

Instructions

Run daily PR monitoring check. Fetches all open PRs, enriches with CI status, reviews, and conflicts, then returns a prioritized summary.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • packages/core/src/commands/daily.ts:630-634 (handler)
    The `runDaily` function serves as the handler for the 'daily' tool, invoking `executeDailyCheck` after ensuring a GitHub token is present.
    export async function runDaily(): Promise<DailyOutput> {
  // Token is guaranteed by the preAction hook in cli.ts for non-LOCAL_ONLY_COMMANDS.
  const token = requireGitHubToken();
  return executeDailyCheck(token);
}
  • packages/mcp-server/src/tools.ts:64-74 (registration)
    The 'daily' tool is registered in the MCP server using the `runDaily` function imported from `@oss-autopilot/core/commands`.
    // 1. daily — Run daily PR check
server.registerTool(
  'daily',
  {
    description:
      'Run daily PR monitoring check. Fetches all open PRs, enriches with CI status, reviews, and conflicts, then returns a prioritized summary.',
    inputSchema: {},
    annotations: { readOnlyHint: false, destructiveHint: false },
  },
  wrapTool(runDaily),
);

Tool Definition Quality

A4/5.0
Behavior3/5

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

Annotations declare readOnlyHint=false (implies side effects) and destructiveHint=false. The description adds valuable context about data aggregation (CI status, reviews, conflicts) and enrichment logic, but fails to explain what non-destructive mutation occurs that makes this not-read-only.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two well-structured sentences. First establishes operation scope (daily check), second details data flow (fetch → enrich → return). No redundancy; every clause adds distinct information about behavior.

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?

Adequately compensates for lack of output schema by describing the return value ('prioritized summary'). Explains the multi-source data aggregation (PRs, CI, reviews, conflicts) which addresses moderate complexity. Minor gap: unclear if summary is returned or persisted given readOnlyHint=false.

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?

Zero parameters present. Per rules, baseline score is 4 for empty parameter schemas. Description appropriately requires no parameter explanation.

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?

Clear specific verb sequence (run/fetch/enrich/return) and resource (PRs). The 'daily' framing and 'prioritized summary' output distinguish this from siblings like 'read' (individual) or 'status' (check), positioning it as the bulk monitoring/reporting tool.

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 term 'daily' implies intended usage (scheduled monitoring), but lacks explicit when/when-not guidance. Does not clarify when to use this versus 'read', 'status', or 'search' for on-demand checks.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/costajohnt/oss-autopilot'

If you have feedback or need assistance with the MCP directory API, please join our Discord server