Skip to main content
Glama
Sign In
Sharphy

Sharphy

by baharmaulidiii
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

sharphy_diff_assemblies

Compares two compiled .NET assemblies at ECMA-335 metadata level to detect added/removed types, API breaking changes, and modified method CIL, helping validate library updates and regressions.

Instructions

Compares two versions of a compiled .NET assembly at the ECMA-335 metadata level to identify added/removed types, API breaking changes, and unified line-by-line CIL instruction diffs. Use this tool when validating library updates, regression testing, or detecting API modifications. Do NOT use for decompiling full method bodies (use 'sharphy_decompile_method'). Read-only comparison.

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": {
      "oldAssemblyPath": "<oldAssemblyPath>",
      "newAssemblyPath": "<newAssemblyPath>"
    },
    "name": "sharphy_diff_assemblies"
  }
}

Input Schema

NameRequiredDescriptionDefault
includeCilDiffNoWhether to include unified line-by-line CIL instruction diff for modified method bodies
newAssemblyPathYesPath to the updated/newer assembly
oldAssemblyPathYesPath to the baseline/older assembly

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.1.0
    • addedInput schema / properties / includeCilDiff
      Added value: +{
+  "default": true,
+  "description": "Whether to include unified line-by-line CIL instruction diff for modified method bodies",
+  "type": "boolean"
+}
  2. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

No annotations are provided, so the description carries the full burden; it does declare 'Read-only comparison', the granularity of analysis (metadata level), and that CIL diffs are unified line-by-line. It stops short of stating anything about output volume, performance on large assemblies, or what happens if paths are invalid, so it is strong but not exhaustive for a no-annotation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences: capability first, usage scenarios second, exclusion plus safety note last. Nothing is redundant and the most decision-relevant content is front-loaded.

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?

No output schema exists, but the description enumerates the main result categories (added/removed types, breaking changes, CIL diffs), so an agent knows what comes back. It lacks detail on result shape/size for large assemblies, a minor gap given the otherwise complete picture.

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 100%, so all three parameters (oldAssemblyPath, newAssemblyPath, includeCilDiff) are already documented in the schema; baseline 3 applies. The description reinforces the role of the baseline/newer pairing and the CIL diff toggle in prose but adds no syntax, format, or constraint detail beyond the schema.

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 (compares) and resource (two versions of a compiled .NET assembly) plus the level of comparison (ECMA-335 metadata, CIL instruction diffs). It enumerates the concrete outputs (added/removed types, breaking changes, CIL diffs), which distinguishes it sharply from metadata-inspection and decompilation siblings.

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?

Gives concrete positive scenarios (validating library updates, regression testing, detecting API modifications) and an explicit exclusion with a named alternative: 'Do NOT use for decompiling full method bodies (use sharphy_decompile_method)'. That is exactly the when/when-not/alternative structure an agent needs to route between siblings.

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