Skip to main content
Glama

gc_memory_read_struct

Read GameCube emulator memory at a given address and unpack it using a Python struct format, returning values in format order for interpreting binary game data.

Instructions

Read memory at address and unpack it with a Python struct format.

fmt is a Python :mod:struct format string, e.g. ">12f" for twelve big-endian floats (a 3x4 transform matrix), ">II" for two big-endian u32 values, or ">4h" for four big-endian s16 values.

GameCube is big-endian, so include a byte-order prefix in fmt: > (big-endian, standard sizes) or ! (network order). If you omit it the format uses the host's native byte order/sizes, which is almost never what you want for a GameCube, so it is recommended to always prefix with >.

The result values is a list of the unpacked values in format order.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "instance_id": "<instance_id>",
      "address": "<address>",
      "fmt": "<fmt>"
    },
    "name": "gc_memory_read_struct"
  }
}

Input Schema

NameRequiredDescriptionDefault
fmtYes
addressYes
instance_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description must carry the behavioral load; it does disclose that the operation is a read and that the return is a list of unpacked values. It adds a genuinely useful pitfall warning about byte order and native sizes, but says nothing about permissions, address validity, or error behavior for out-of-range addresses.

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?

The purpose is front-loaded in the first sentence and the fmt examples are efficient. The byte-order paragraph repeats itself slightly ('almost never what you want' plus 'recommended to always prefix with >'), which could be one sentence instead of two.

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

Completeness3/5

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

There is no output schema, but the description usefully explains the return value as a list of unpacked values in format order. Against 0% schema coverage and three required parameters, leaving instance_id entirely undocumented is a real gap for a tool of this complexity.

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 0%, so the description has to compensate. It documents 'fmt' thoroughly with three concrete examples and byte-order prefix advice, and implies 'address' is the read location, but gives no format details for address and never mentions 'instance_id' at all.

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?

States a specific verb and resource ('Read memory at address and unpack it with a Python struct format'), which is concrete enough to distinguish it from a plain raw memory read. However, it never names or contrasts with the sibling gc_memory_read, so the differentiation is left to inference.

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 only implied: an agent can infer this is the tool for structured multi-value reads rather than raw byte dumps. There is no explicit when-to-use/when-not guidance and no reference to gc_memory_read or gc_memory_write_struct as alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.