Skip to main content
Glama

Compare two pulls

compare
Read-only

Identify what changed between two pulls from history: rows added, removed, changed, and totals that moved.

Instructions

Compare two pulls from history (e.g. a pull and its tweak): rows added, rows removed, rows whose numbers changed, and totals that moved, from pull_id to other_pull_id. Uses the rows both pulls kept (see keep_rows), else re-runs both. Its rows go where a query's do: the results panel, or a capped preview with more_rows for the rest.

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": {
      "pull_id": "<pull_id>",
      "other_pull_id": "<other_pull_id>"
    },
    "name": "compare"
  }
}

Input Schema

NameRequiredDescriptionDefault
pull_idYes
other_pull_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnly/not-destructive/closed-world, so the description's added value is the execution model: it reuses rows both pulls kept (see keep_rows) and otherwise re-runs both, warning that the call may be costly. It also discloses that output is capped into a preview with more_rows for the remainder, which materially affects how an agent interprets partial results.

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 action and its outputs, then cost behavior, then result routing — a sensible ordering with no filler. The third sentence is dense and packs keep_rows, query, and more_rows references into one clause, which is efficient but slightly heavy.

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

Completeness3/5

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

For a two-parameter read-only tool with no output schema, the description covers the semantic payload (the four diff categories) and result routing well. It leaves gaps on what the comparison output looks like structurally and when the re-run path triggers versus the cached path, which matters for a tool whose cost can vary.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% with two bare string parameters, so the description must carry the load — and it does by fixing the direction of the comparison ("from `pull_id` to `other_pull_id`"), implying pull_id is the base and other_pull_id the target. It does not clarify formats or where the IDs come from, so it stops short of full coverage.

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 ("Compare two pulls from history") and enumerates the diff categories produced: rows added, rows removed, rows with changed numbers, and moved totals. The parenthetical example ("a pull and its tweak") plus the direction "from `pull_id` to `other_pull_id`" separates it cleanly from history and tweak siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The directionality clause implies which pull is the baseline and which is the comparison, and naming keep_rows and more_rows points at related flows. However, it never states explicitly when to reach for compare rather than history or tweak, and offers no when-not guidance; usage must be inferred from the diff-category list.

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