Skip to main content
Glama
Sign In
total-agent-memory

total-agent-memory

by vbcherepanov
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

memory_wiki_generate

Idempotent

Generates per-project wiki digests as Markdown files, summarizing key decisions, solutions, conventions, and recent changes. Optionally target a specific project or refresh all active projects.

Instructions

v10 — Render the per-project wiki digest (top decisions, active solutions, conventions, recent changes) as Markdown. Pass project to refresh one wiki, omit it to refresh all active projects. Files land in <MEMORY_DIR>/wikis/.md and are deterministic (no LLM call).

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": "memory_wiki_generate"
  }
}

Input Schema

NameRequiredDescriptionDefault
projectNoProject to refresh (omit for all)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

Discloses side effects: files land in <MEMORY_DIR>/wikis/<project>.md, and states determinism. The 'refresh' wording implies overwriting and writing to disk, consistent with readOnlyHint=false. IdempotentHint=true aligns with deterministic behavior. Some details about whether existing files are overwritten or other memory structures change are not explicit, but the core behavior is transparent.

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?

Two concise sentences with no filler. All key information—purpose, parameter usage, output location, and determinism—is packed efficiently and logically ordered.

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?

Covers purpose, parameter semantics, side effects, and determinism. It does not specify the exact Markdown structure or define 'active projects', but given the tool's simplicity and the presence of sibling tools for detailed queries, this is sufficient for an agent to invoke it correctly.

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?

The schema description ('Project to refresh (omit for all)') is clear, and the tool description reinforces it with concrete behavior ('refresh one wiki' vs 'all active projects'). This adds a bit of context beyond the schema, clarifying the optional parameter's effect on scope.

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 (render) and resource (per-project wiki digest), and enumerates the digest contents (top decisions, active solutions, conventions, recent changes). This clearly distinguishes the tool from memory-related siblings without needing to name them.

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?

Provides explicit parameter usage: pass `project` to refresh one wiki, omit it to refresh all active projects. It also notes the tool is deterministic (no LLM call), helping an agent decide when to use it. It doesn't explicitly mention when-not alternatives, but the purpose is sufficiently unique.

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