Skip to main content
Glama

update_memory

Update an existing memory or architectural decision in place by ID while keeping its record ID and creation timestamp. Use it to revise titles, content, tags, status, or category without breaking references.

Instructions

Update an existing memory or architectural decision in-place by its ID without losing its record ID or creation timestamp.

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": {
      "id": "<id>"
    },
    "name": "update_memory"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesNumeric ID of the memory record to update.
tagsNoOptional updated tags array.
titleNoOptional updated title.
statusNoOptional updated status.
contentNoOptional updated explanation or decision content.
categoryNoOptional updated category.
workspaceNoOptional updated workspace identifier.
supersedesNoOptional list of memory IDs this record supersedes.
source_agentNoName of the AI tool updating this memory (e.g. 'antigravity').

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.0

TDQS

B3.1/5.0
Behavior3/5

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

With no annotations, the description carries the full behavioral burden. It does disclose one genuinely useful trait beyond the schema: the update is in-place and preserves the record ID and creation timestamp. However, it says nothing about partial-update semantics (are unspecified fields cleared or retained?), permission requirements, or what happens when supersedes is set.

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 sentence with zero filler text; every clause contributes to meaning. It loses a point only because the lone sentence packs purpose and one behavioral guarantee together without any structure for usage or caveats.

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?

This is a nine-parameter mutation tool with no annotations and no output schema, so the description must do more. It omits partial-update behavior, the effect of supersedes on other records, status-transition semantics versus deprecate_memory, and any return/error information.

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 description coverage is 100%, so the baseline is 3 and the schema already documents all nine parameters including both enums. The description adds only that id targets an existing record and that timestamps survive, without clarifying interaction rules such as how supersedes affects the referenced records or how status transitions behave.

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 uses a specific verb (update) on a specific resource (an existing memory or architectural decision) and adds a scoping qualifier ('by its ID', 'in-place'), which clearly separates it from creation-type siblings like remember_decision and deletion siblings like delete_memory. It does not explicitly name or contrast with any sibling, so it stops 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 Guidelines2/5

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

There is no explicit when-to-use or when-not-to-use guidance; the only implied condition is that the record already exists. Critically, the schema's status enum includes 'deprecated' and a sibling named deprecate_memory exists, yet the description offers no routing guidance between updating status here versus using that dedicated tool.

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