Skip to main content
Glama
Sign In
Errata MCP Server

Errata MCP Server

Official
by formachines-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Check a package version

check_package
Read-only

Checks PyPI or npm packages for sandbox-verified corrections to outdated AI-written code, returning apply, lead, or none verdicts with reasons for the installed version.

Instructions

Corrections for a PyPI or npm package where AI models write outdated code, each verified in a sandbox, with verdict apply / lead / none for the installed version and the reason. Apply on your own only verdict apply (checked on the installed version, proof.auto_apply true); show a lead to the user, a newer version than the checked ones included.

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": {
      "ecosystem": "<ecosystem>",
      "package": "<package>"
    },
    "name": "check_package"
  }
}

Input Schema

NameRequiredDescriptionDefault
packageYes
versionNoinstalled version (exact), or a range if that is all you know
ecosystemYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.2

TDQS

A3.8/5.0
Behavior4/5

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

Beyond readOnlyHint/openWorldHint, the description discloses that corrections are individually verified in a sandbox, that verdicts carry a reason, and that auto-apply eligibility is gated by a proof.auto_apply flag on the exact installed version. That trust-tier information is exactly the behavioral context an agent needs before acting on results. It never contradicts the annotations.

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

Conciseness3/5

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

Two sentences with no filler, but the opening clause is grammatically tangled ('Corrections for a PyPI or npm package where AI models write outdated code') and the second sentence is a run-on stitched together with parentheticals. The operational rule is buried mid-sentence rather than front-loaded.

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 usefully enumerates the return shape (verdict enum plus reason) and the auto-apply condition, which is enough for a three-parameter read-only lookup. Minor gaps remain around whether version is optional and what happens when no corrections exist, but nothing critical for correct invocation is 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?

Schema coverage is only 33% (only 'version' is documented in the schema), so the description must compensate. It does clarify that the version should be the installed exact version and that ecosystem is pypi or npm, but the 'package' parameter's expected format (bare name vs. scoped/namespaced) is never addressed.

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?

The description makes clear that the tool surfaces sandbox-verified corrections for a PyPI or npm package where AI models commonly write outdated code, and that results come back as verdicts (apply / lead / none) tied to the installed version. The verb is implicit rather than stated ('Corrections for...'), and nothing distinguishes it from the sibling tools search_error and report, but an agent can still tell what it retrieves.

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?

It gives explicit action rules for the result: apply autonomously only when verdict is 'apply' with proof.auto_apply true on the installed version, otherwise surface the lead to the user, including when a newer version than the checked ones exists. What is missing is when to call this tool at all versus search_error or report, so the routing guidance is one-sided.

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