Skip to main content
Glama
gregordadera

aicb-roslyn-mcp

by gregordadera
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

Estimate Impact of a Change

impact_of_change
Read-onlyIdempotent

Estimate a C# symbol's change impact before editing: get direct and transitive dependents, production impact, and risk level to see what a rename or signature change could break.

Instructions

Estimate the blast radius of changing a symbol: its direct users plus their dependents, with a risk level.

Call it first, before any edit to a symbol other code names (a rename, signature, default value): a compile checks names, not what a consumer assumes.

Returns directCount and transitiveCount (one per declaration, tests included), productionImpactCount (transitive, without tests), risk and directImpact (at most 20; items {name, file, line} as in find_usages). risk reads productionImpactCount: 0 none, 1-4 low, 5-20 medium, above 20 high; it counts dependents, not what the change means. Where one cycle dominates a high closure, a 'saturation' block leads the counts and risk reads the direct production fan-in.

Per kind: a type - the closure of the types that reference it; a method or operator - its caller closure through interface and abstract dispatch; a property, field, event or enum member - the code that touches it (transitive = direct). A qualified method also counts its contracts' callers ('viaContract', as in find_usages).

An interface or abstract method or type adds 'implementers' per contract (count, testCount, typeCount, testTypeCount, members): what a signature change breaks. Then risk reads 'riskBasis'.total = closure + implementers (production implementing types; on a type only direct ones the closure lacks; 'indirect' lists those via a base class). 'namesakes' splits an entry same-named contracts share; 'riskBasis'.note flags no production caller.

A 'note' ahead of the counts flags misleading numbers: directCount 0 on a resolved symbol (DI or reflection may reach it), unresolved core references, productionImpactCount 0 on an all-test solution, and 'not_found' (risk 'none' is no measurement; 'nearest' gives a close name). 'collision' names a same-named symbol of another kind, not counted.

Read-only. symbol is case-sensitive and resolves as in find_usages: a type by its simple name, a member bare (one kind) or as 'Type.Member'. A constructor ('Type.Type') is not resolved here: use find_usages.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
symbolYesThe exact (case-sensitive) type, method, property, field, event, enum-member or operator (metadata) name to assess - or the qualified Type.Member form for a member.
sessionIdYesThe session_id returned by analyze_solution. Also takes an absolute .sln/.slnx/.slnf path, analyzed on first use.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.5.46514
    • changedInput schema / properties / symbol / description
      Previous value: -"The exact (case-sensitive) type, method, property, field, event or enum-member name to assess - or the qualified Type.Member form for a member."New value: +"The exact (case-sensitive) type, method, property, field, event, enum-member or operator (metadata) name to assess - or the qualified Type.Member form for a member."
  2. 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."
  3. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnlyHint/idempotentHint and no destruction, so safety is covered; the description goes far beyond that with return fields (directCount, transitiveCount, productionImpactCount, directImpact, risk), the risk thresholds tied to productionImpactCount, per-kind closure semantics, implementers/riskBasis behavior, and the note/not_found/collision caveats that flag misleading counts.

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?

Long and dense, but front-loaded (purpose, then call-order guidance, then return/behavior details) and nearly every clause carries distinct information. The remaining cost is readability: the risk-threshold and note/collision material is packed tightly enough that it slows scanning.

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?

There is no output schema, so the description must carry return-value meaning, and it does: exact field names, risk mapping, per-kind closure definitions, and edge-case blocks (saturation, implementers, namesakes, note, collision). Little an agent needs to interpret results is missing.

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, but the description meaningfully extends the symbol parameter: case-sensitivity, simple-name vs bare-member vs 'Type.Member' resolution, and that constructors are not resolved. That is genuine semantic value beyond the schema text.

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 ('Estimate the blast radius of changing a symbol: its direct users plus their dependents, with a risk level') and immediately scopes it as the pre-edit step. It also distinguishes itself from find_usages by adopting its resolution rules while carving out constructors, so an agent can tell what it does and does not cover.

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 use trigger ('Call it first, before any edit to a symbol other code names (a rename, signature, default value)') with the reason (compile checks names, not consumer assumptions). It names the alternative for an excluded case: a constructor 'is not resolved here: use find_usages'.

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