Skip to main content
Glama

decompile_batch

Destructive

Decompile multiple functions matching a name filter in parallel, with per-function and total output limits; optionally write all results uncapped to a specified file.

Instructions

Decompile many functions matching a name filter, in parallel, 6000 chars each and 40000 in all; out=<file.c> writes all uncapped to a file under the output root, kept unless overwrite=true. For one use decompile.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "decompile_batch"
  }
}

Input Schema

NameRequiredDescriptionDefault
outNoA file under the output root, not with filter or a max: .c every function (over 4096 blocks: cut); .h, .ct, .rcnet the mod SDK as C++ header, Cheat Engine table, ReClass.NET.
filterNoCase-insensitive filter on function name or entry hex.
libraryNoWith out: also write library functions (default false).
overwriteNoWith out: replace an existing file (default false).
max_functionsNoMaximum functions to decompile (default 10, max 50).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.2.6
    • changedInput schema / properties / out / description
      Previous value: -"A `.c` file under the output root to write every function to; not with `filter` or `max_functions`."New value: +"A file under the output root, not with filter or a max: .c every function (over 4096 blocks: cut); .h, .ct, .rcnet the mod SDK as C++ header, Cheat Engine table, ReClass.NET."
  2. Changed1 schema field changedv0.2.2
    • changedInput schema / properties / out / description
      Previous value: -"Write every function to this `.c` file instead, uncapped, leaves\nfirst; not with `filter` or `max_functions`. Relative to the output\nroot, or absolute under it."New value: +"A `.c` file under the output root to write every function to; not with `filter` or `max_functions`."
  3. First observedv0.2.1

TDQS

A4.5/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing concrete caps (6000 chars each, 40000 total), that `out=` bypasses the caps, and that the written file persists unless `overwrite=true`. This complements destructiveHint=true by explaining exactly what writing does. It does not contradict the annotations; only omission is any note on error behavior when the output root is unwritable.

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?

A single dense sentence with the primary mode front-loaded and the alternative trailing. Every clause carries information (caps, file output, overwrite, sibling), though the semicolon-heavy packing makes it slightly harder to parse than a two-sentence split would be.

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 and a destructive write mode, the description supplies the essential missing context: output size limits, file destination rules, and overwrite protection. Remaining gaps (return shape when no `out` is given, per-file vs per-call truncation details) are minor for a 5-param tool with fully documented schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, and the description genuinely adds meaning: it explains the `out` vs capped-return tradeoff, the persistence/`overwrite` semantics, and that `filter` selects the function set. `max_functions` and `library` are left entirely to the schema, keeping it short of a 5.

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+resource ('Decompile many functions') plus the selection scope ('matching a name filter') and the parallelism trait. It explicitly points to the sibling `decompile` for the single-function case, so an agent can separate the two without reading either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Names the alternative ('For one use decompile') and the condition that selects this tool (many functions, name-filtered). It also explains the two operating modes: inline capped output vs `out=<file.c>` writing uncapped to disk.

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