Skip to main content
Glama
carloshpdoc

memorydetective

Diff reference-tree class counts and classify abandoned-memory shape

analyzeAbandonedMemory

Detect non-cyclic memory leaks by comparing before/after snapshots and classifying class growth shapes to reveal orphaned observers, never-removed handlers, and cache issues.

Instructions

[mg.memory] Compare two .memgraph snapshots on heap reference-tree class counts (NOT cycle list) and classify each class's growth shape. Surfaces the family of bugs the cycle-only diffMemgraphs misses: orphaned KVO observers, never-removed NotificationCenter handlers, caches that never evict, singleton-retained payloads, and the long tail of unknown-growth worth manual inspection.

Pair with the verify-fix loop: captureScenarioState({label:'before'}) -> ship fix -> captureScenarioState({label:'after'}) -> analyzeAbandonedMemory(beforePath, afterPath). Validated end-to-end on the notelet investigation where AVPlayerItem went 342 to 0 across a fix that was invisible in standard leaks output (leakCount: 0 both sides).

Returns growthByClass[] ranked by absolute delta, each entry tagged with classification (kvo-observer-orphaned, notificationcenter-observer-leaked, cache-too-aggressive, singleton-retains-payload, unknown-growth) + confidence tier + hint. The classifier escalates large co-occurrence growth: if NSKeyValueObservance grew, other large-delta classes are assumed to be the observed types being retained, classified as kvo-observer-orphaned with confidence scaling by delta size.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
beforePathYesAbsolute path to the baseline `.memgraph` (the BEFORE snapshot). Use `captureScenarioState({ label: 'before' })` to produce one in the standard verify-fix flow.
afterPathYesAbsolute path to the post-fix `.memgraph` (the AFTER snapshot). Same workflow as `beforePath`, after applying the candidate fix.
topNNoCap on `growthByClass[]` length. Default 25, max 200. Classes are ranked by absolute instance-count delta descending.
classFilterNoOptional substring filter. When set, only classes whose name contains this substring are included in the response. Useful for verifying a specific class went to baseline without seeing the surrounding noise.
outputFormatNoResponse format. Omitted or `json` (default, preserves v1.8 behavior) returns JSON.stringify of the result. `markdown` renders a human-readable view of the same data. `both` returns both content items in one response, so a client can display markdown to the user and parse JSON for the agent loop without a second call. `verify-fix-table` (v1.10, applies to `analyzeAbandonedMemory` and `diffMemgraphs`) emits a focused 4-column markdown comparison table (Class | Before | After | Delta) of the actionable rows; other tools fall back to `markdown` for this value.
Behavior5/5

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

No annotations present, so description fully covers behavior: compares reference-tree counts (not cycles), classifies into specific categories with confidence scaling, and explains co-occurrence escalation logic. Output structure detailed.

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?

Well-structured with clear front-loading of purpose, but somewhat verbose with detailed examples and classification logic. Could be trimmed while retaining value.

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, but description thoroughly explains return structure (growthByClass array with classification, confidence, hint). Covers all necessary context for a complex memory analysis tool.

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% with descriptive parameter descriptions. The tool description does not add extra meaning beyond what's in the schema, so baseline of 3 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?

The description clearly states it compares two .memgraph snapshots on heap reference-tree class counts and classifies growth shapes, distinguishing it from diffMemgraphs which only handles cycles. The verb 'analyze' and resource 'abandoned memory' are specific.

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?

Explicit workflow provided: pair with verify-fix loop using captureScenarioState before/after, and a real validation example. Implicitly suggests when not to use (e.g., cycle-only bugs) by contrasting with diffMemgraphs.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/carloshpdoc/memorydetective'

If you have feedback or need assistance with the MCP directory API, please join our Discord server