Skip to main content
Glama

ui_save_memory

Save or update project memory entries from the UI to preserve architecture, conventions, commands, constraints, pitfalls, context, and facts for later reuse.

Instructions

App-only: create or update a project memory entry from the UI.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "project_id": "<project_id>",
      "title": "<title>",
      "content": "<content>"
    },
    "name": "ui_save_memory"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyNo
tagsNo
titleYes
sourceNo
contentYes
categoryNo
memory_idNo
confidenceNo
file_pathsNo
project_idYes
inject_modeNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.7/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the entire behavioral burden and discloses almost nothing. "Create or update" implies an upsert, but it never says how update mode is triggered (memory_id? key?), whether existing content is overwritten, what permissions or conflict rules apply, or what the caller gets back. For an 11-parameter mutation tool with zero annotation coverage, this is a major gap.

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?

A single front-loaded clause with zero filler; the "App-only" constraint is placed first, which is the right ordering. The brevity is efficient, though here it reflects under-specification rather than disciplined editing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 11 parameters, four enums, no annotations, and no output schema, this tool is complex, yet the definition is one sentence that explains neither the create-vs-update mechanics nor any parameter meaning. Only the app-only scope and the resource are established.

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?

Schema description coverage is 0% across 11 parameters, including four enums (source, category, confidence, inject_mode) whose allowed values appear with no explanation of effect. The description adds only an indirect hint that entries are project-scoped, leaving the agent unable to tell how memory_id, key, and inject_mode change behavior.

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?

The description gives a specific verb pair ("create or update") and a specific resource ("a project memory entry"), plus a scope qualifier ("App-only ... from the UI") that distinguishes it from non-UI siblings like memory_save. It stops short of naming the sibling it differs from, so the agent must infer the boundary.

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

Usage Guidelines2/5

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

"App-only" is a scope restriction rather than usage guidance: it tells the agent the tool is tied to the UI app but not when to choose it over memory_save, note_save, or ui_save_note. There are no exclusions, prerequisites, or conditions under which the create path versus the update path should be taken.

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