Skip to main content
Glama

Compare Bundles

compare_bundles
Idempotent

Compare two canonical Evidence bundles by exact records, explicit observation pairs, and full revision histories; return digest-anchored inline changes and flag omissions as non-equivalence.

Instructions

Compare two canonical Evidence bundles by exact record membership, explicit one-to-one observation pairs, and complete residual-unknown revision histories. Missing bundle members describe omission only, never behavioral equivalence; output is digest-anchored and returns every change inline.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "record_pairs": [],
      "left_bundle_path": "/tmp/left-evidence.json",
      "right_bundle_path": "/tmp/right-evidence.json"
    },
    "name": "compare_bundles"
  }
}

Input Schema

NameRequiredDescriptionDefault
record_pairsNo
left_bundle_pathYesLocal filesystem path for left bundle.
right_bundle_pathYesLocal filesystem path for right bundle.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare idempotent=true and destructive=false, so safety is partly covered. The description adds real value beyond them: it discloses that output is digest-anchored, that every change is returned inline, and a semantic rule that absent records mean omission rather than equivalence. The surprising readOnlyHint=false for a comparison operation is left unexplained, which keeps this from a 5.

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?

Two sentences, front-loaded with the verb and object, with no filler. The phrasing is dense with specialized jargon ('residual-unknown revision histories', 'digest-anchored') but each clause carries distinct information rather than restating the name.

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?

No output schema exists, so the description must carry return behavior; it does point to inline changes and digest anchoring but does not explain the response structure, error cases for missing paths, or what the digest is anchored to. Adequate for the three-parameter surface, but not complete for an agent needing to interpret results.

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?

With 67% schema coverage, both path parameters and the nested observation-pair fields are already documented in the schema. The phrase 'explicit one-to-one observation pairs' reinforces the semantics of record_pairs (pairing, not bulk diffing) but adds no syntax or format detail, so the baseline 3 applies.

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?

States a specific verb and resource ('Compare two canonical Evidence bundles') and enumerates the comparison dimensions: record membership, one-to-one observation pairs, residual-unknown revision histories. An agent can distinguish this from compare_source_to_bundle or compare_artifacts on the 'two bundles' scope, though the description never names a sibling explicitly.

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 '"canonical Evidence bundles'" constraint implies when this applies, and the sentence about missing members being 'omission only, never behavioral equivalence' implies a when-not-to-infer rule. But there is no explicit guidance on when to pick this over compare_source_to_bundle or which situations call for a bundle-to-bundle diff at all.

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