Skip to main content
Glama

Inspect Native Instruction

inspect_native_instruction
Idempotent

Decode a code or data address to view bytes, mnemonic, operands, control flow, and typed incoming/outgoing references; distinguishes data, interior instruction, and undecodable-byte outcomes.

Instructions

Inspect one exact code or data address: decoded bytes, mnemonic, ordered operand tokens, flow, outgoing instruction references and typed incoming references where available. Incoming references preserve source, access kind, operand index and analysis provenance even at data addresses; they do not prove runtime access. Memory addressing decomposition is unavailable when the provider supplies only tokens. Data, interior instruction addresses and undecodable bytes are distinct outcomes.

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": {
      "address": "0x1000"
    },
    "name": "inspect_native_instruction"
  }
}

Input Schema

NameRequiredDescriptionDefault
addressYes
documentNoExact provider document or program identity.

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?

Goes well beyond the annotations by disclosing what incoming references carry (source, access kind, operand index, provenance), warning that they do not prove runtime access, and flagging that memory addressing decomposition is unavailable when the provider supplies only tokens. These are real interpretation caveats an agent could not derive from the hint flags. Note the tension between the purely observational framing and readOnlyHint=false, though the description never explicitly claims read-only behavior, so this is not a direct contradiction.

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?

Three sentences, front-loaded with the verb and scope, then return content, then caveats. Dense but every clause conveys distinct information; only the final sentence's three-way outcome list is somewhat compressed into jargon.

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?

With no output schema, the description carries the full burden of describing returns, and it does so thoroughly: bytes, mnemonic, operand tokens, flow, outgoing refs, and typed incoming refs with their field set. What's left thin is parameter-level guidance for document and any error/not-found semantics for the 'distinct outcomes' it mentions.

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 50%: the address field is undocumented in the schema, and the description partially compensates by implying it must be a single exact code or data address. The document parameter's role (provider document/program identity) is covered only by the schema, and the description adds nothing about how it interacts with address selection.

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?

Opens with a specific verb and resource ('Inspect one exact code or data address') and enumerates the outputs (decoded bytes, mnemonic, operand tokens, flow, refs), which makes it clearly an address-level inspector rather than a function- or module-level tool. It never names a sibling or contrasts against inspect_address_context or annotate_native_function, so differentiation is inferred from scope wording rather than stated.

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 phrase 'one exact code or data address' implicitly tells the agent this is for single-address queries, and the closing sentence distinguishes data addresses, interior instruction addresses and undecodable bytes as separate outcomes. There is no explicit when-to-use/when-not-to-use guidance and no pointer to an alternative for function-level or boundary-level questions.

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