Skip to main content
Glama

list_agent_memory

Discover which instruction and memory files each coding agent reads for a repository and compare them to reveal rules one agent sees but another misses.

Instructions

Show which instruction and memory files each agent reads for a repository, and the drift between them (rules one agent sees but another doesn't).

Covers CLAUDE.md, Claude auto-memory, AGENTS.md (Codex/Cursor/OpenCode), GEMINI.md, .cursor/rules, and Codex memories at project and user level.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "list_agent_memory"
  }
}

Input Schema

NameRequiredDescriptionDefault
projectNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

B3.3/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full burden. It does disclose scope (project and user level, specific file families) and that drift detection is part of the result, which goes beyond the bare name. It never states that the operation is read-only, what access or permissions are needed to read user-level files, or what happens if files are missing, leaving meaningful behavioral gaps.

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?

Two sentences, front-loaded with the core action and followed by a scannable coverage list. The file-type enumeration earns its place by letting an agent judge applicability. Minor waste only in the parenthetical agent-vendor list.

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?

Complexity is low (one optional parameter, output schema present, so return values need no explanation) and the description covers what is inspected and the drift concept. The remaining hole is the meaning and default of 'project', which the schema does not document either.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is one optional parameter ('project') with 0% schema description coverage. The phrase 'for a repository' hints that project identifies a repo, but the description never says whether it is a path, name, or ID, nor what the null default means (current directory, all projects, repo root discovery). The single undocumented parameter is the main call-time ambiguity.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Show which instruction and memory files each agent reads for a repository, and the drift between them.' An agent can tell this is an inspection/read operation over memory files. It does not explicitly name a contrasting sibling (e.g. sync_memory for writes, suggest_instruction_updates for fixes), so it falls short of a 5.

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

Usage Guidelines3/5

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

The second paragraph enumerates exactly which file types and levels are covered (CLAUDE.md, AGENTS.md, .cursor/rules, project vs user level), which implicitly tells the agent when this tool applies. But there is no explicit when-to-use vs when-not guidance and no mention of alternatives such as sync_memory or suggest_instruction_updates for acting on the drift found.

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