Skip to main content
Glama

Trace Native Ui Action

trace_native_ui_action
Idempotent

Traces a compiled UI action, object ID, native symbol, or function address through authored connections, Objective-C handlers, and bounded static call references to map native UI call paths.

Instructions

Trace one unique compiled UI action, object ID, native symbol or exact function address through authored connections, encoded or symbolized Objective-C handlers, and bounded static call references. Typed direct and resolved indirect calls, ambiguous candidates, inferred untyped provider callees, and targetless sites remain distinct. Runtime reachability is unknown; use trace_native_values for recovered value dependencies.

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": {
      "action": "buildTapped:",
      "max_depth": 8,
      "max_edges": 500,
      "max_nodes": 250
    },
    "name": "trace_native_ui_action"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYesA unique compiled UI action selector, interface object ID, native symbol or exact function address
max_depthNoMaximum permitted depth for this operation.
max_edgesNoMaximum permitted edges for this operation.
max_nodesNoMaximum permitted nodes for this operation.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing that typed direct and resolved indirect calls, ambiguous candidates, inferred untyped provider callees, and targetless sites are kept distinct, and that traversal is bounded and static-only. It does not reconcile the notable tension that readOnlyHint=false, idempotentHint=true, and destructiveHint=false imply a state-affecting yet repeatable operation while "trace" reads as pure analysis, nor does it describe result volume or cost.

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?

Three sentences, front-loaded with the purpose, then result semantics, then caveat plus alternative. No filler, and the dense terminology is load-bearing rather than decorative.

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 four-parameter static-analysis tool with no output schema, the definition covers what is traversed, how result categories differ, the static-only limitation, and where to go for value dependencies. The remaining gap is that the annotation profile (readOnlyHint=false) is never explained, leaving an agent unsure whether invoking it has side effects.

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% and the schema documents all four parameters, so the baseline is 3. The description only alludes to the budget parameters via the phrase "bounded static call references" and adds no meaning about how max_depth, max_edges, or max_nodes interact or what happens when a budget truncates the trace.

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 ("Trace") and a precisely enumerated resource (one unique compiled UI action, object ID, native symbol, or exact function address), plus the connection types traversed. It also routes the value-dependency case to the named sibling trace_native_values, so an agent can distinguish it from its neighbors without opening any schema.

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?

Gives an explicit alternative for one case ("use trace_native_values for recovered value dependencies") and a clear caveat that runtime reachability is unknown, which tells the agent when this tool's answer is insufficient. It lacks a broader statement of when to prefer this over siblings like trace_call_path or trace_android_references, so it stops short of full routing guidance.

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