Skip to main content
Glama

Trace Application Feature

trace_application_feature
Idempotent

Trace a typed literal seed across all reachable parts of an authenticated JavaScript Application Graph, using inline Evidence or retained same-session references while preserving authority boundaries.

Instructions

Trace a typed literal seed through every reachable part of an authenticated JavaScript Application Graph supplied as inline Evidence or exact same-session retained references. Original static, native, passive-runtime, inferred, and unknown authorities remain distinct; native addon handoffs never open a provider or execute the application.

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": {
      "seed": {
        "kind": "module",
        "match": "exact",
        "value": "renderer.js",
        "case_sensitive": false
      },
      "direction": "both",
      "application": {
        "kind": "retained-evidence",
        "evidence_id": "ev_2a6371cd2a7665bdad6d37d9b3a69da558e9882a0696d195f1f1a7707f14b5e5"
      }
    },
    "name": "trace_application_feature"
  }
}

Input Schema

NameRequiredDescriptionDefault
seedYes
directionNoDirection in which to traverse or compare relationships.
applicationYes
native_observationsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior4/5

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

Beyond the annotations, it discloses real behavioral traits: authority provenance is preserved as distinct classes (static, native, passive-runtime, inferred, unknown), and native addon handoffs do not open a provider or execute the application. It leaves one annotation-driven question unanswered — readOnlyHint=false implies some state is written or recorded, yet the description reads like a pure analysis pass and never says what is persisted or retained.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the verb and scope, with no filler. The density of undefined jargon ('typed literal seed', 'authenticated graph', 'authority') makes it slower to parse than its length suggests.

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

Completeness2/5

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

There is no output schema and the description says nothing about the shape of the returned traversal (nodes, edges, per-authority partitions, coverage status), which is the central deliverable of a trace tool. Combined with 25% schema coverage and an unexplained native_observations parameter, an agent cannot confidently predict inputs or outputs from this definition alone.

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

Parameters2/5

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

Schema description coverage is only 25%, so the description must carry the load: it clarifies the seed (a typed literal, not a free-form pattern) and the application (inline Evidence versus retained reference), which is genuine added meaning. However, 'direction' is never mentioned and 'native_observations' — a required-field-heavy array of evidence objects — is completely unexplained, leaving two of four parameters opaque.

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?

Names a specific verb ('Trace') and target ('a typed literal seed through every reachable part of an authenticated JavaScript Application Graph'), which is concrete enough to distinguish it from binary-analysis siblings. It never names or explicitly contrasts with close siblings such as trace_feature or trace_javascript_semantics, so the differentiator must be inferred from the 'JavaScript Application Graph' qualifier.

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 description states a precondition (the graph must be an 'authenticated JavaScript Application Graph' supplied either as inline Evidence or 'exact same-session retained references'), which is usable guidance about acceptable inputs. It gives no when-to-use versus-when-not guidance and never points at an alternative tool for related traversals.

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