Skip to main content
Glama

Compare Application Versions

compare_application_versions
Idempotent

Compare two authenticated JavaScript Application Graph versions from inline/retained Evidence to report added, removed, changed, ambiguous, unknown entities; changed_from graph without fuzzy pairing.

Instructions

Compare two authenticated JavaScript Application Graph versions supplied as inline Evidence or exact same-session retained references. Uses unique-only exact digest, module source digest, source-map identity, structural fingerprint, and non-module semantic-key tiers. Reports added, removed, changed, ambiguous, and unknown entities plus the complete matching changed_from graph without fuzzy or module-ordinal pairing.

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": {
      "left": {
        "kind": "retained-evidence",
        "evidence_id": "ev_2a6371cd2a7665bdad6d37d9b3a69da558e9882a0696d195f1f1a7707f14b5e5"
      },
      "right": {
        "kind": "retained-evidence",
        "evidence_id": "ev_3ce65a02b9646af31ae60860daa94775bda12e25e480aa767459b20e60e8eec9"
      }
    },
    "name": "compare_application_versions"
  }
}

Input Schema

NameRequiredDescriptionDefault
leftYesLeft-hand input used for comparison or differential execution.
rightYesRight-hand input used for comparison or differential execution.
left_native_observationsNo
right_native_observationsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

The description adds genuine behavioral guarantees beyond annotations: matching uses exact digest, module source digest, source-map identity, structural fingerprint and semantic-key tiers, explicitly 'without fuzzy or module-ordinal pairing'. However, annotations declare readOnlyHint=false and idempotentHint=true, and the description never explains what side effect makes this a non-read-only operation (e.g., recording evidence or mutating session state), which is the single most important thing an agent needs to know here.

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 action and the input contract before the matching-tier detail. The second sentence is a dense enumeration of tiers and result categories, but each item carries information; the jargon ('semantic-key tiers', 'changed_from graph') is the only drag on readability.

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 correctly spends its second half enumerating return content: added, removed, changed, ambiguous, unknown entities plus the complete matching changed_from graph. The remaining gap is operational rather than descriptive — the readOnlyHint=false side effect, error behavior for non-authenticated inputs, and the native-observation parameters go unexplained.

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 50%: left and right carry only generic 'Left-hand input used for comparison or differential execution' text, and left_native_observations / right_native_observations are undocumented in the schema. The description partially compensates by defining the accepted input forms ('inline Evidence or exact same-session retained references'), including the same-session constraint that the schema's $ref union does not convey, but it says nothing about the two native-observation parameters.

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 opens with a specific verb+resource pair ('Compare two authenticated JavaScript Application Graph versions'), which is far more precise than the bare name and scopes it to JavaScript Application Graph artifacts rather than arbitrary binaries or bundles. It does not name the near siblings (compare_bundles, compare_javascript_export_shapes, compare_functions), so an agent must infer the boundary from the resource noun alone.

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?

Usage is implied rather than stated: inputs must be 'inline Evidence or exact same-session retained references', which tells the agent what it may pass but not when to pick this over compare_bundles or compare_javascript_export_shapes. There is no explicit when-not guidance, no prerequisite checklist, and no mention of what happens if the two versions are not authenticated.

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