Skip to main content
Glama

inspect

Analyze binary files and game assets by module and action, covering PE/APK/Unity/Unreal structures, tables, archives, entropy maps, and hex views for modding workflows.

Instructions

Inspect files/structures. Dispatches by module+action.

Modules: pe, apk, unity, unreal, tables, archives, format, hex. Actions: pe: pe_info (path), find_function (path, name|string_ref) apk: apk_manifest (apk_path), native_lib_info (so_path), resource_extract (apk_path, out_dir, pattern) unity: unity_assets (path, action=list|extract) unreal: unreal_pak (pak_path, action=list|extract) tables: list_entries (path, schema) archives: unpack (archive_path, out_dir) format: entropy_map (path, block_size) hex: hex_view (path, offset, limit) Large outputs are paginated via offset/limit inside params.

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": {
      "module": "<module>",
      "action": "<action>"
    },
    "name": "inspect"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYes
moduleYes
paramsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior2/5

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

With no annotations, the description carries the full behavioral burden, and it is silent on the most consequential trait: several actions clearly write to disk (resource_extract takes out_dir, unity_assets and unreal_pak accept action=extract, archives/unpack takes out_dir), yet nothing flags these as mutating versus the read-only listing actions. It does disclose that large outputs are paginated via offset/limit, which is genuinely useful context. It omits file-size limits, permission requirements, and failure behavior for a tool operating on arbitrary binaries.

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 line is front-loaded, then a clean module-grouped list, then a one-line note on pagination. Every line carries routing information an agent needs, and the indentation mirrors the module/action nesting of the call. Minor redundancy in repeating out_dir across entries, but no filler sentences.

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?

An output schema exists, so return-value explanation is rightly absent, and the dispatch table covers the parameter naming gap left by a 0% covered schema. What is missing is proportionate to complexity: for a 16-action tool with no annotations, the description should mark which actions write files or consume large resources. As-is, an agent must guess the destructive profile of extract/unpack calls before invoking them.

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 description coverage is 0% and neither module nor action has an enum, so the description is doing necessary work by listing valid modules and the per-action parameters (e.g. find_function takes path plus name|string_ref, entropy_map takes path and block_size). That compensates materially for the empty schema. It still leaves meaning unstated: no format/units for offset, limit, or block_size, no explanation of what pattern expects in resource_extract, and no guidance on whether paths are absolute.

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?

The first sentence gives a specific verb and resource ('Inspect files/structures') and the module/action dispatch table makes the scope concrete by enumerating 16 named operations across pe, apk, unity, unreal, tables, archives, format, and hex. An agent can tell this is a binary/file analysis entry point rather than a search or edit tool. It stops short of 5 because it never explicitly contrasts itself with siblings like diagnose, search, or validate, so the boundary is inferred from action names 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 description supplies routing guidance ('Dispatches by module+action') and task-oriented action names such as find_function, entropy_map, and hex_view let an agent infer which entry point to pick. However, there is no explicit when-to-use or when-not-to-use statement, no prerequisites, and no mention of when a sibling tool would be the better choice. Usage is implied by the dispatch table rather than instructed.

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