Skip to main content
Glama

Trace Native Values

trace_native_values
Idempotent

Trace a bounded static dependency graph from a native procedure to map def-use chains, constants, memory and branch operations, and resolved call edges for data-flow analysis.

Instructions

Trace a bounded static dependency graph from one explicit native procedure. Includes high-p-code def-use, constants, operators, memory and branch operations, resolved call edges, and derived argument/parameter and return/output bindings. Missing bindings, alias semantics, persistent state and RNG roles remain unknown. Budgets bound depth, decompilations, graph size and payloads; nodes are paginated.

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": {
      "limit": 1000,
      "offset": 0,
      "max_depth": 3,
      "max_edges": 10000,
      "max_nodes": 5000,
      "procedure": "0x1000",
      "max_functions": 16,
      "max_call_sites": 256
    },
    "name": "trace_native_values"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
offsetNo
max_depthNoMaximum permitted depth for this operation.
max_edgesNoMaximum permitted edges for this operation.
max_nodesNoMaximum permitted nodes for this operation.
procedureYes
max_functionsNoMaximum permitted functions for this operation.
max_call_sitesNoMaximum permitted call sites for this operation.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already carry the safety profile (openWorldHint=false, idempotentHint=true, destructiveHint=false), so the burden is lower, and the description still adds real behavioral context: it names the explicit limitation set (missing bindings, alias semantics, persistent state, RNG roles remain unknown) and discloses that budgets bound depth, decompilations, graph size and payloads, plus that results are paginated. That is materially useful for interpreting partial results. It does not explain why readOnlyHint is false for what reads like a static analysis pass, which is the remaining gap.

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?

Four sentences, each doing distinct work: purpose, contents, known limitations, resource controls. The purpose is front-loaded and the limitation sentence prevents over-trusting results. Density is high and domain jargon ("high-p-code def-use") is load-bearing rather than filler, though it assumes domain fluency.

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 an 8-parameter tool with no output schema, the description covers what kind of graph is produced, which edge/relation classes are resolved, what is deliberately left unknown, and how budgets and pagination constrain the result. An agent can call this correctly and interpret results with appropriate caution. The missing piece is the side-effect posture implied by readOnlyHint=false and any linkage to a prior session/binary handle.

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 63% and the schema descriptions are generic boilerplate ("Maximum permitted depth for this operation"), so the description does add value by mapping budgets to concrete concerns: depth, decompilations (max_functions/max_call_sites), graph size (max_nodes/max_edges) and payloads (limit/offset). It also reinforces that exactly one procedure identifier is accepted. It still gives no sense of how to choose budget values or what the defaults mean, so it lands at the baseline-plus level rather than fully compensating.

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?

"Trace a bounded static dependency graph from one explicit native procedure" gives a specific verb (trace), a specific artifact (static dependency graph), and a specific anchor (one native procedure). It further enumerates what the graph contains (def-use, constants, operators, memory and branch operations, call edges, argument/parameter and return bindings), which separates it from siblings such as trace_call_path or inspect_native_instruction. It stops short of naming an alternative outright, so it is clear but not fully sibling-differentiating.

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: the agent can infer this is the tool for mapping data flow out of a single native routine, and the sentence about missing bindings, alias semantics, persistent state and RNG roles tells the agent when the output will be insufficient. However, there is no explicit "use this instead of X when Y" routing and no stated prerequisite (e.g. an analyzed binary session), which leaves the choice among several trace_* siblings to inference.

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