Skip to main content
Glama

Compare a record between commits

compare_record
Read-onlyIdempotent

Track specific changes within a single record between two commits. Review every field modification to view the values before and after a historical update.

Instructions

What changed in one record between two commits: each field that changed, with its value before and after. Take the commits from record_history or list_branches.

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": {
      "type": "<type>",
      "id": "<id>",
      "from": "<from>",
      "to": "<to>"
    },
    "name": "compare_record"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesThe record's id, as Type/local (LearningObjective/lateral-reading-check) or the local part alone.
toYesThe later commit id.
fromYesThe earlier commit id.
typeYesThe record's class, such as LearningObjective, AssessmentItem, Module or DesignNote.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds value beyond them by disclosing the return shape: a per-field before/after diff. It stops short of describing behavior when a record is absent at one of the commits.

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 short sentences, zero filler, with the core purpose front-loaded and the input-sourcing hint trailing. Every clause earns its place.

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?

For a 4-parameter read-only diff tool with full schema coverage and no output schema, the description covers purpose, output content and input provenance. Only the edge cases (commits out of order, record missing at one commit) are left implicit.

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 type, id, from and to are fully documented in the schema, including the Type/local id form and the earlier/later commit distinction. The description adds no syntax or format details beyond what the schema already provides, which is the expected baseline here.

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 — 'What changed in one record between two commits' — and immediately clarifies granularity ('each field that changed, with its value before and after'). This separates it from record_history, which supplies the commits rather than the diff.

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?

Explicitly routes the agent to record_history or list_branches for the commit ids, which is the key prerequisite for calling this tool. It does not, however, contrast it with get_record (point-in-time read) or state what happens if the commits are unrelated.

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