Skip to main content
Glama
gregordadera

aicb-roslyn-mcp

by gregordadera
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

Get Architecture Overview

architecture_overview
Read-onlyIdempotent

Map a C#/.NET solution's architecture without full source: layer, service, class, role, entry-point, and hotspot graphs, bounded for large codebases and production-focused.

Instructions

Orient on a whole solution WITHOUT the firewall of full source. When anything was cut, the document LEADS with a block: how many sections were capped, how many entries are shown of how many in total, and one 'SECTION: shown of total' row per capped section - read it before the sections, because the per-section '+N more' lines below state one section's loss each and never the whole. Absent = nothing was cut. Renders a structural-only AI-Builder-Markdown overview: the macro/architecture graphs (layer map, service & class dependency graphs, role graph, entry points + entry-point flow, architecture flow, interface relations) plus a domain summary and a quality-hotspots section (the most complex methods + most-coupled types) - but NO per-type/per-file source-code blocks, so it stays bounded where export_markdown is a 27-29 MB firehose. BOUNDED AT SCALE: each macro section is capped at 80 entries with a '+N more' note; the layer map lists every type up to 2000 and per-layer counts above, so even a 200+-project monolith returns a usable orientation instead of overflowing the token cap (use export_markdown for the full set, or find_symbol / call_graph / get_context to drill in). PRODUCTION-FOCUSED: test projects are excluded by default (an architecture overview is otherwise dominated by every test method listed as an entry point + its flow trace, which is not part of the production architecture) - set includeTests=true to include .Tests/.Spec projects. Method-level call graphs are deliberately omitted (use call_graph / explain_symbol for a specific symbol). Multi-TFM solutions are deduplicated to one logical project per name, keeping the NEWEST TFM's instance (without it every hotspot/edge appears once per TFM). Recall-safe: works on live AND recalled sessions (on a recalled session quality-hotspot line counts are unavailable, complexity is still shown). Use this FIRST to understand a codebase's shape, then get_context / explain_symbol to drill into a symbol.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
leanNoLean mode (default TRUE): drop the <AI_CONTEXT_SPEC>/<AI_CONTEXT_META> format-rules preamble and any empty graph sections. Set false for the full AI-Builder-MD document contract.
sessionIdYesThe session_id returned by analyze_solution. Also takes an absolute .sln/.slnx/.slnf path, analyzed on first use.
summaryOnlyNoSummary mode (default FALSE): collapse each macro-section to a count + top-N entries instead of up to 80. Use on EXTREME/very-large solutions (200+ projects, heavy generics) where even the bounded overview exceeds the token cap and would otherwise return nothing.
includeTestsNoInclude test projects (default FALSE - production focus: an architecture overview is otherwise flooded by every test method listed as an entry point + its flow trace, bloating the output with scaffolding that is not part of the production architecture). Set true to include *.Tests/*.Spec projects in the graphs.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.5.46513
    • changedInput schema / properties / sessionId / description
      Previous value: -"The session_id returned by analyze_solution."New value: +"The session_id returned by analyze_solution. Also takes an absolute .sln/.slnx/.slnf path, analyzed on first use."
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description is free to disclose traits the annotations cannot: the LEADING <TRUNCATION> block and how to read it, the 80-entry-per-section cap with '+N more' rows, the 2000-type layer-map ceiling, multi-TFM deduplication to the newest TFM, and degraded behaviour on recalled sessions. That is genuinely useful context beyond structured fields.

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?

Front-loaded with the single most important fact (whole-solution orientation, bounded output) and organized with emphatic labels (BOUNDED AT SCALE, PRODUCTION-FOCUSED, Recall-safe). It is dense and parenthetical-heavy, with some restatement of schema-level guidance, but little of it is wasted.

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

Completeness5/5

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

No output schema exists, so the description carries the burden of describing the return shape and does so in detail: truncation block semantics, section list, domain summary, quality-hotspots contents, and what is absent. Combined with the token-cap and capping behaviour, an agent has everything needed to call it and interpret the result.

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 four parameters are already documented in the schema, including the same rationales for lean/includeTests/summaryOnly. The description mostly restates those defaults and conditions rather than adding new syntax or semantics, so the baseline 3 for schema-carried parameters is appropriate.

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 and resource ('Orient on a whole solution', 'Renders a structural-only AI-Builder-Markdown overview') and enumerates exactly which graphs are included and which are deliberately not (no per-type/per-file source blocks, no method-level call graphs). It explicitly distinguishes itself from siblings export_markdown, call_graph, explain_symbol and get_context.

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 an explicit ordering: 'Use this FIRST to understand a codebase's shape, then get_context / explain_symbol to drill into a symbol.' It names alternatives with the condition that selects them (export_markdown for the full set, find_symbol/call_graph/get_context to drill in, includeTests for test projects, summaryOnly for 200+ project monoliths).

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