Skip to main content
Glama
Sign In
rarefaction

rarefaction

by ip2k
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Working set for a change

scope
Read-onlyIdempotent

Identify files a symbol change is likely to touch—callers, callees, implementations, tests, and historically co-changed files—to plan edits and know what to read and check.

Instructions

The files a change to one symbol is likely to touch: orient's call-graph files (callers, callees, implementations, tests) plus files that have historically changed in the same commits as the symbol's file, each with its reason. Use when planning an edit, to know which files to read and check. Advisory, not a boundary: real changes often touch files outside it.

Input Schema

NameRequiredDescriptionDefault
upNoHow many levels of callers to walk (default 2: test cases usually sit one helper above the code they exercise).
downNoHow many levels of callees to walk (default 1).
symbolYesA function, method, type or property: "updateLocation", "Engine.updateLocation", or an exact position "Sources/Engine.swift:204:10" (1-based line:column, on the name).
profileNoSource-language profile; required for bare names in mixed workspaces.
projectNoWorkspace-relative project directory, e.g. tools/driver for a nested Cargo package. Without it, a path:line:column symbol is answered from its enclosing Cargo workspace, else from its nearest project marker (a warning says when that leaves part of the workspace out).
max_nodesNoMaximum graph nodes per direction and reference contexts; lower it for compact answers.

Output Schema

NameRequiredDescriptionDefault
rootYes
filesYesThe working set: symbol file first, then call-graph files, then files found only through history or links.
statsYes
countsYes
symbolYes
profileYes
warningsYes
co_changeYes
truncatedYesThe call-graph walk hit max_nodes.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changedv0.4.2
    • changedInput schema / properties / project / description
      Previous value: -"Workspace-relative project directory, e.g. tools/driver for a nested Cargo package."New value: +"Workspace-relative project directory, e.g. tools/driver for a nested Cargo package. Without it, a path:line:column symbol is answered from its enclosing Cargo workspace, else from its nearest project marker (a warning says when that leaves part of the workspace out)."
    • removedOutput schema / properties / co_change / properties / anchor_commits / maximum
      Removed value: -9007199254740991
    • removedOutput schema / properties / co_change / properties / anchor_commits / minimum
      Removed value: --9007199254740991
    • changedOutput schema / properties / co_change / properties / anchor_commits / type
      Previous value: -"integer"New value: +"number"
    • addedOutput schema / properties / counts / properties / link_only
      Added value: +{
+  "maximum": 9007199254740991,
+  "minimum": -9007199254740991,
+  "type": "integer"
+}
    • changedOutput schema / properties / counts / required
      Previous value: -[
-  "files",
-  "call_graph",
-  "co_change",
-  "co_change_only",
-  "project_source_files"
-]New value: +[
+  "files",
+  "call_graph",
+  "co_change",
+  "co_change_only",
+  "link_only",
+  "project_source_files"
+]
    • changedOutput schema / properties / files / description
      Previous value: -"The working set, symbol file first, then call-graph files, then co-change-only files."New value: +"The working set: symbol file first, then call-graph files, then files found only through history or links."
    • changedOutput schema / properties / files / items / properties / sources / items / enum
      Previous value: -[
-  "symbol",
-  "call_graph",
-  "co_change"
-]New value: +[
+  "symbol",
+  "call_graph",
+  "co_change",
+  "link"
+]
  2. Addedv0.3.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already establish readOnly/idempotent/closed-world, so the description focuses on what annotations cannot say: that results are advisory and incomplete by nature, and that each file comes with a reason. That reliability caveat is genuinely useful and not derivable from the schema.

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 sentences: composition, when to use, and the key caveat — front-loaded with the resource definition and no filler. Every sentence contributes distinct information.

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 an output schema present and 100% parameter coverage, the description only needs to frame purpose and limitations, which it does. Minor gap: it doesn't hint at profile/project resolution caveats, though the schema carries those details.

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 coverage is 100%, so parameter documentation is already fully handled. The description only indirectly illuminates the up/down depth parameters via the caller/callee/test enumeration; it adds no syntax or default guidance beyond what the schema states.

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?

The description names the concrete output — the set of files a change to one symbol is likely to touch — and specifies how that set is composed (callers, callees, implementations, tests plus historically co-changed files). This is clearly distinct from the sibling `orient` (call-graph) and `status`, so an agent can choose without opening the schema.

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

Usage Guidelines4/5

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

"Use when planning an edit, to know which files to read and check" gives an explicit triggering situation, and "Advisory, not a boundary" sets expectations about when not to over-trust the result. It stops short of naming an alternative tool or a when-not-to-call condition.

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