Skip to main content
Glama

Diastella

Check my change

check_my_change
Read-onlyIdempotent

Ask this after editing and before committing: does this change undo a past fix? Give the change as a unified diff (the output of git diff). For every past fix (a merged change that closed a bug report) whose lines the diff removes or rewrites, returns the fix, the bug report it closed, how many of the lines it added to that file are being removed, and the tests that fix added, so they can be run before the change is kept. A test the diff itself deletes is named too. tests_to_run lists the tests that past fixes added for the files in the diff, whether or not a line of theirs is removed. A change that removes no such line is reported as that; it is not a promise that the change is safe. The diff is read to answer and is not kept.

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": {
      "repository": "<repository>",
      "diff": "<diff>"
    },
    "name": "check_my_change"
  }
}

Input Schema

NameRequiredDescriptionDefault
diffYes
repositoryYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, and the description adds substantial context on top: the diff 'is read to answer and is not kept', exactly what is returned per matched fix, that `tests_to_run` is computed from files in the diff regardless of line removal, and that an empty result 'is not a promise that the change is safe'. That last caveat is exactly the kind of guidance annotations cannot express.

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?

Front-loaded with the trigger and the input format before unpacking the return value, which is the right order. The middle sentences are dense and clause-heavy (the long enumeration of returned fields), but every sentence conveys a distinct fact and the safety caveat earns its space.

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, so the description must describe results itself — and it does, field by field, including the `tests_to_run` semantics and the deleted-test case. It is nearly complete for a two-parameter read tool; the only real omission is the meaning and format of `repository`.

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 0%, so the description carries the full burden. It defines `diff` well as a unified diff and names `git diff` as the source, but says nothing about `repository` — its expected form (URL, owner/name, path) or how it relates to the diff's paths is left entirely to inference. Since one of two required parameters is undefined, it compensates only partially for the coverage gap.

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: it takes a diff and reports whether that change removes or rewrites lines that past fixes introduced. The closing clause enumerates the return payload (the fix, the bug report it closed, line-removal counts, the tests the fix added), which makes the tool's function unmistakable even among looks-related siblings like before_you_change.

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?

Gives an explicit trigger: 'Ask this after editing and before committing.' That is a clear placement in the workflow and matches the tool's purpose. It stops short of naming when not to use it or pointing to an alternative sibling for a different question, so it does not reach the top band.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources