Skip to main content
Glama

Link Memories

link_memories

Create a directed link from one of the caller's personal memories to another in the same space.

edge_kind says how the from memory relates to the to memory. Linking a pair that is already linked with the same kind returns that link with changed=false. Errors: NotFound (a memory is not visible to you), InvalidArgument (the same memory twice, or an unknown kind), Conflict.

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": {
      "from_memory_id": "<from_memory_id>",
      "to_memory_id": "<to_memory_id>"
    },
    "name": "link_memories"
  }
}

Input Schema

NameRequiredDescriptionDefault
edge_kindNosupports, contradicts, derives_from, or references (default).references
to_memory_idYesmemory_id (UUID) of the memory the link points to; must differ from from_memory_id.
from_memory_idYesmemory_id (UUID) of the memory the link starts from.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • changedInput schema / properties / edge_kind / description
      Previous value: -"Input value for the Link Memories tool."New value: +"supports, contradicts, derives_from, or references (default)."
    • removedInput schema / properties / edge_kind / title
      Removed value: -"Edge Kind"
    • changedInput schema / properties / from_memory_id / description
      Previous value: -"Input value for the Link Memories tool."New value: +"memory_id (UUID) of the memory the link starts from."
    • removedInput schema / properties / from_memory_id / title
      Removed value: -"From Memory Id"
    • changedInput schema / properties / to_memory_id / description
      Previous value: -"Input value for the Link Memories tool."New value: +"memory_id (UUID) of the memory the link points to; must differ from from_memory_id."
    • removedInput schema / properties / to_memory_id / title
      Removed value: -"To Memory Id"
    • removedInput schema / title
      Removed value: -"link_memoriesArguments"
  2. Added

TDQS

A4.4/5.0
Behavior4/5

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

Adds substantial behavior beyond the annotations: dedup semantics with a changed=false return, and a concrete error taxonomy (NotFound for invisible memories, InvalidArgument for self-link or unknown kind, Conflict). One tension worth noting: the stated same-kind dedup behavior reads as idempotent, while the annotations declare idempotentHint=false — likely because a different edge_kind on an existing pair does create a new edge, but the description could make that distinction explicit.

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 sentences, front-loaded with the operation, then the key parameter semantics, then a compact error list. No filler and no restatement of the tool name or title.

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?

For a 3-parameter mutation with no output schema, the description covers the operation, edge direction, dedup outcome, and error cases — enough to call it correctly. It does not say what the returned link object contains beyond the changed flag, though with no output schema that omission is minor.

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?

Schema coverage is already 100%, so the baseline is 3, but the description adds real meaning the schema lacks: it defines the directionality of the edge (edge_kind expresses how the from memory relates to the to memory), which matters for a directed relationship. The self-link error restates the schema's 'must differ' constraint, so that portion is redundant.

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 and resource — 'Create a directed link from one of the caller's personal memories to another' — plus the scoping constraints ('caller's personal', 'in the same space') and the edge direction. An agent can distinguish this from relationship-removal or relationship-listing siblings without opening the schema.

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?

Gives clear context for use: pick an edge_kind describing how the from memory relates to the to memory, and linking a pair already linked with the same kind is a no-op returning changed=false. It does not explicitly name an alternative tool (e.g., for removing or inspecting links) or state when not to use it, so it stops short of full routing guidance.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.