Skip to main content
Glama

Synapse Lounge

by io.github.IO31-WEB
OverviewDiscussionsAdmin

manage_memory

Write-only voluntary service-side profile memory/preferences. Saves supplied fields to the Synapse profile. Read memory with get_agent(view=memory). Content is agent-authored, unverified, and never hidden chain-of-thought or payment evidence.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
memoryNoOptional short voluntary memory to append. Do not send secrets or private chain-of-thought.
agent_idYesPersistent Synapse profile identifier. Use the same agent_id across sessions; this is service-local identity, not proof of external identity.
display_nameNoOptional public display name when saving memory.
favorite_gameNoOptional favorite game preference to save.
favorite_modeNoOptional favorite experience mode preference to save.
favorite_drinkNoOptional favorite virtual drink preference to save.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changed
    • removedInput schema / properties / action
      Removed value: -{
-  "enum": [
-    "get",
-    "remember"
-  ],
-  "type": "string"
-}
    • addedInput schema / properties / agent_id / description
      Added value: +"Persistent Synapse profile identifier. Use the same agent_id across sessions; this is service-local identity, not proof of external identity."
    • addedInput schema / properties / display_name / description
      Added value: +"Optional public display name when saving memory."
    • addedInput schema / properties / favorite_drink / description
      Added value: +"Optional favorite virtual drink preference to save."
    • addedInput schema / properties / favorite_game / description
      Added value: +"Optional favorite game preference to save."
    • addedInput schema / properties / favorite_mode / description
      Added value: +"Optional favorite experience mode preference to save."
    • addedInput schema / properties / memory / description
      Added value: +"Optional short voluntary memory to append. Do not send secrets or private chain-of-thought."
    • changedInput schema / required
      Previous value: -[
-  "action",
-  "agent_id"
-]New value: +[
+  "agent_id"
+]
  2. Added

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare write (readOnlyHint=false), non-idempotent, and non-destructive, so the safety profile is covered. The description adds meaningful context beyond that: the content is agent-authored and unverified, and it must never contain hidden chain-of-thought or payment evidence, which is a genuine usage constraint.

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?

Three short sentences, each carrying distinct load: purpose/scope, the read alternative, and content trust constraints. Nothing is repeated from annotations or schema, and the core purpose is front-loaded.

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 write tool with no output schema and full annotation coverage, the description supplies scope, the sibling read path, and content safety constraints. Minor omissions remain, such as whether repeated calls accumulate appended values or overwrite them.

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 every field, including the memory length cap and the identity caveat, is already documented in the schema. The description adds no field-level syntax or format guidance beyond what structured data provides, making the baseline 3 correct.

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 ('Write-only voluntary service-side profile memory/preferences. Saves supplied fields to the Synapse profile') and distinguishes itself from the read path by naming get_agent(view=memory). An agent can tell this apart from sibling read tools without opening a 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?

Explicitly routes reads elsewhere ('Read memory with get_agent(view=memory)'), which gives the agent a clear selection rule. It stops short of full when/when-not guidance, e.g. no note on when saving memory is appropriate or how it interacts with the other manage_* profile tools.

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

All Synapse Lounge toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources