Skip to main content
Glama
Sign In
Mushi-Mushi

Mushi-Mushi

by kensaurus
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

CI cost fix bundle (one PR, several fixes)

get_ci_cost_fix_bundle
Read-onlyIdempotent

Read a CI cost fix bundle by bundleId to inspect its draft PR, per-workflow fixes, status, and measured monthly savings after merge. Use it to track rollout results and verify cost reductions.

Instructions

Read one CI cost fix bundle (one draft PR for several fixes in one repo, from apply_ci_cost_fix_rollout) by its bundleId: { bundle: { id, projectId, repo, status (queued | running | pr_opened | nothing_opened | failed), prUrl, prNumber, items (each fix: workflowPath, kind, status, summary, error, prUrl, baseline, measured, saving), measuredUsdPerMonth (after the merge: the saving measured per workflow, each workflow once) } }. After the merge it reads GitHub once and stores the minutes per day since. Read-only on GitHub.

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": {
      "bundleId": "<bundleId>"
    },
    "name": "get_ci_cost_fix_bundle"
  }
}

Input Schema

NameRequiredDescriptionDefault
bundleIdYesresults[].bundleId from apply_ci_cost_fix_rollout

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.19

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and idempotentHint, so the safety profile is covered; the description adds real behavioral context beyond that — a single GitHub read after merge and cached per-day minute storage, plus the full status lifecycle (queued | running | pr_opened | nothing_opened | failed). It does not address how fresh the stored data is or what a failed bundle read returns.

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 and provenance are front-loaded in the opening clause, and the long field enumeration earns its place because no output schema exists. The inline prose-embedded object literal is dense and harder to scan than a structured listing, which is the main deduction.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and a single param, the description carries the return-shape burden itself — bundle fields, per-item fix fields, savings, and measuredUsdPerMonth semantics are all spelled out, along with the post-merge GitHub read. Nothing an agent needs to call it correctly appears missing.

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?

Only one parameter with 100% schema description coverage, so the schema already carries the load. The description reinforces provenance ('by its bundleId' from apply_ci_cost_fix_rollout) but adds no format or edge-case semantics beyond what the schema states.

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 — read one CI cost fix bundle by bundleId — and pins down what a bundle is (one draft PR for several fixes in one repo). It also names the producing sibling, apply_ci_cost_fix_rollout, so an agent can distinguish it from get_ci_costs, get_ci_bill, and get_ci_overview at a glance.

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?

Clear context is given: this reads a bundle created by apply_ci_cost_fix_rollout, and the bundleId parameter is explicitly sourced from that tool's results. No exclusions or 'use X instead when...' guidance for the other CI cost siblings, but the workflow position is unambiguous.

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