Skip to main content
Glama

Import Managed Reconstruction

import_managed_reconstruction
Idempotent

Import decompiler-produced managed reconstruction against authenticated inspect_managed_members evidence, lock methods to artifact/metadata hashes, and mark C#/pseudocode as analyst inference.

Instructions

Import decompiler-produced managed reconstruction against authenticated inspect_managed_members Evidence. The workflow locks each method to artifact SHA-256, MVID, metadata token, signature hash, and the limited decoded-IL tuple hash, records the decompiler identity and options, and marks C# or pseudocode as analyst inference rather than canonical byte observation.

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": {
      "static_members": "<static_members>",
      "decompiler": "<decompiler>",
      "methods": "<methods>"
    },
    "name": "import_managed_reconstruction"
  }
}

Input Schema

NameRequiredDescriptionDefault
notesNo
methodsYes
decompilerYes
static_membersYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, so safety framing is partly covered. The description adds substantive behavior beyond that: per-method provenance locking to artifact SHA-256, MVID, metadata token, signature hash and decoded-IL tuple hash, recording of decompiler identity/options, and the epistemically important rule that C#/pseudocode is recorded as analyst inference rather than byte observation. It does not describe behavior on duplicate or conflicting imports, which is the main 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?

Two sentences, both dense with meaning, with the core action and its evidence prerequisite front-loaded before the provenance and classification details. The phrasing is jargon-heavy (MVID, tuple hash) but every clause carries behavioral information; 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?

This is a mutation tool with no output schema, so the description must explain what the agent gets back and what can go wrong, and it does neither. It is complete on provenance and epistemic classification, but silent on return value, conflict/duplicate handling despite idempotentHint=true, and validation failure modes for the heavily constrained schema.

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% at the top level, so the description must carry the parameter burden. It does map meaning onto 'decompiler' (identity, family, options) and 'methods' (token, signature_sha256, normalized_il_sha256, reconstruction kind/language/text), and it gestures at the evidence object via 'authenticated inspect_managed_members Evidence', but it never explains 'static_members' or 'notes', leaving two of four parameters unaddressed.

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 description gives a specific verb ('Import') and a specific resource ('decompiler-produced managed reconstruction'), and it names the required upstream sibling, inspect_managed_members, whose authenticated Evidence is the input. That makes it distinguishable from the inspection tools, though it does not explicitly contrast with other import-family siblings such as import_evidence_bundle.

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?

A prerequisite is stated implicitly: reconstruction must be imported 'against authenticated inspect_managed_members Evidence,' so the agent knows inspection must happen first. However, there is no explicit when-to-use/when-not-to-use guidance, no mention of what to do if the Evidence is missing or does not match, and no routing to alternatives such as verify_reconstruction.

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