Skip to main content
Glama

memory_update

Modify existing stored information by updating content, metadata, or tags to maintain accurate and current data records.

Instructions

Update an existing memory. Only provided fields are updated.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
memory_idYes
contentNo
metadataNo
tagsNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • Tool handler for 'memory_update' which updates an existing memory entry. It uses an internal _update_memory function and then schedules a cloud graph sync.
    async def memory_update(
        memory_id: int,
        content: Optional[str] = None,
        metadata: Optional[Dict[str, Any]] = None,
        tags: Optional[list[str]] = None,
    ) -> Dict[str, Any]:
        """Update an existing memory. Only provided fields are updated."""
        try:
            record = _update_memory(memory_id, content, metadata, tags)
        except ValueError as exc:
            return {"error": "invalid_input", "message": str(exc)}
        if not record:
            return {"error": "not_found", "id": memory_id}
        _schedule_cloud_graph_sync()
        return {"memory": record}
Behavior3/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It successfully communicates the partial-update semantics (PATCH-like behavior), which is critical. However, it omits mutation safety details (reversibility, atomicity), error handling for non-existent IDs, and authorization requirements.

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?

The description consists of two efficient sentences with no redundancy. The first sentence establishes the operation, and the second delivers essential behavioral context (partial updates). Every word earns its place; no restructuring is needed.

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

Completeness3/5

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

Given the presence of an output schema (per context signals), the description appropriately omits return value details. For a 4-parameter update tool with no annotations, it covers the critical behavioral trait (partial updates) but lacks completeness regarding error conditions (e.g., 404 scenarios) and prerequisites (memory existence), preventing a higher score.

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 0%, requiring the description to compensate significantly. The description adds value by explaining that unspecified fields are left unchanged (implying the optional nature of content, metadata, and tags). However, it fails to define what these fields represent (e.g., what format metadata accepts) or that memory_id is the identifier required to locate the target.

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 clearly states the core action ('Update an existing memory') with a specific verb and resource. While it distinguishes broadly from siblings like memory_create or memory_delete through the verb choice, it does not clarify nuanced differences versus tools like memory_merge or memory_patch (if one existed).

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 phrase 'Only provided fields are updated' provides implicit guidance on when to use this tool (for partial updates) versus potentially replacing an entire memory. However, it lacks explicit 'when to use' guidance compared to siblings like memory_create_batch or memory_merge, and does not mention prerequisites like the memory needing to exist.

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/agentic-box/memora'

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