Skip to main content
Glama

What a dependency update breaks in your code

check_upgrade
Read-onlyIdempotent

Call this before or after updating a dependency: pass the package, the version you have, the version you are moving to, and the code that uses the package (a snippet, or several files by path).

Instructions

Call this before or after updating a dependency: pass the package, the version you have, the version you are moving to, and the code that uses the package (a snippet, or several files by path). Returns each use the new version breaks, with its file and line: a removed name, a keyword no longer accepted, a newly required argument, or a call that only raises, with the release that changed it and the replacement. A break is reported only when the new version fails and the old one doesn't; deprecations are warnings, and uses DepTime can't tell about are listed apart, never as breaks. One package per call; for a whole project, deptime check-upgrade reads the version changes from its lockfiles.

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": {
      "package": "<package>",
      "from_version": "<from_version>"
    },
    "name": "check_upgrade"
  }
}

Input Schema

NameRequiredDescriptionDefault
codeNoPython code that uses the package, read with `ast` (never run); its uses are reported at file `<code>`.
filesNoSeveral Python files instead of, or as well as, `code`: relative path -> source. Paths name the uses in the answer. Up to 2,000,000 characters across all of them.
packageYesPyPI distribution name, e.g. 'langchain-core'.
to_versionNoThe version to update to; defaults to the newest indexed release.
from_versionYesThe version the code works with now, e.g. '0.27.2'.

Output Schema

NameRequiredDescriptionDefault
baseNoThe git revision the versions before were read from, if any.
noteNo
breaksNoConfirmed breaks across `checked`; `deptime check-upgrade` exits 1 when > 0.
checkedNo
projectYesThe directory checked, as given; `<code>` for code passed to the check_upgrade tool.
skippedNoPackages added or removed: there's no upgrade to check.
files_readNo
suppressedNoBreaks and notices left out by the project's suppressions; `note` says so.
not_coveredNoChanged packages DepTime doesn't index, so nothing was checked for them.
files_unreadableNoPython files that don't parse, so nothing was read from them (first 20).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.2.2

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, closed-world behavior, and the description adds genuinely new rules beyond that: a break is reported only when the new version fails and the old one does not, deprecations are downgraded to warnings, and uses it cannot analyze are listed separately rather than as breaks. That classification policy is exactly the kind of behavioral context an agent cannot get from the hints. It says nothing about cost, latency, or what happens when the package or version is unknown.

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?

The action and timing lead, the input list follows, then the return semantics and the scope boundary. The enumeration of break kinds and the exception cases each carry distinct information, and no sentence merely repeats the title or schema.

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?

For a five-parameter analysis tool with an output schema and full annotations, the description covers the call timing, the two input forms, the break-vs-warning classification, the unanalyzable-uses bucket, and the single-package limit with a project-level alternative. An agent has everything needed to decide to call it and to interpret the result.

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 100%, so every parameter is already documented in structured form. The description restates the four inputs in plain language (package, current version, target version, code as snippet or files by path) but adds no format, default, or constraint details beyond the schema. Baseline 3 applies when the schema carries the parameter burden.

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 states a specific verb and resource: it returns each use of a package that the target version breaks, with file, line, and the release that changed it. Scope is pinned down ('One package per call'), so an agent can tell it apart from a whole-project check. It stops short of naming any sibling tool, leaving the comparison with check_symbols or diff_versions to inference.

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?

"Call this before or after updating a dependency" gives explicit timing, and the closing sentence establishes the boundary case: a whole project should go through `deptime check-upgrade` reading lockfiles, not this tool. No sibling MCP tool is offered as an alternative for adjacent questions, so routing among the other tools is left unstated.

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