Skip to main content
Glama

Synapse Layer — Trust Infrastructure for AI Agents

by io.github.SynapseLayer

save_to_synapse

Idempotent

Persist memory with encryption at rest, sanitization, and deduplication controls.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tagsNoTags for categorization.
typeNoEvent type: [MILESTONE], [DECISION], [ALERT], [AUTO-STRAT], [AUTO-OP], [AUTO-INSIGHT], [AUTO-DECISION], [AUTO-CONTEXT], [MANUAL].
contentYesThe memory content to store securely.
projectNoProject identifier (e.g., SYNAPSE_LAYER).
subjectNoESCOPO1 (optional): opaque 8-128 char token ([A-Za-z0-9._:-]) that isolates memory to a single person within a shared connect-token. Omit for token-scoped behavior. Never include PII/email.
agent_idNoAgent identifier for memory isolation. Defaults to "default".
importanceNoImportance level 1–5 (default: 3).
force_intentNoMANUAL OVERRIDE ONLY — use apenas quando você (humano) quer forçar explicitamente a classificação de intenção. Valores reconhecidos: preference | fact | procedural | bio | critical | operational | strategic | compliance | security | system_directive | clinical | general | ephemeral. Se não tiver certeza, NÃO preencha este campo — o sistema classifica automaticamente. Valores não reconhecidos são ignorados silenciosamente e retornados em warnings.
intent_reasonNoAuditable reason for forcing intent classification. Max 500 characters. Ignored if force_intent is absent.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
statusYes
memory_idYes
trust_quotientNo

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already signal that this is a write operation (readOnlyHint=false) and idempotent (idempotentHint=true). The description adds context beyond those annotations by mentioning encryption at rest, sanitization, and deduplication controls, though it does not explain how sanitization/deduplication manifest or what side effects to expect.

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?

One front-loaded sentence with no filler, and the core action 'Persist memory' leads. It is appropriately terse, though it could have included routing guidance without becoming verbose.

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?

With an output schema, 100% parameter documentation, and annotations, the agent can invoke it, but the description leaves the sibling-selection question unresolved and does not clarify the behavior of sanitization/deduplication controls. For a 9-parameter tool in a crowded sibling set, this is adequate but not complete.

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 schema fully documents all nine parameters; the description adds no parameter-level meaning. That meets the baseline but does not rise above it.

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 names an explicit operation and resource: 'Persist memory' is a clear verb+object, and the distinguishing features (encryption at rest, sanitization, deduplication controls) separate it from generic siblings such as save_memory. It does not explicitly name or contrast any sibling, so it misses the top score.

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?

No guidance is given about when to use this tool rather than save_memory, store_memory, or recall_memory. The feature list implies secure persistence, but there is no explicit context, condition, or alternative mention for an agent to route correctly.

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

All Synapse Layer — Trust Infrastructure for AI Agents toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.1/5.0
Disambiguation2/5

Several tools are redundant: recall_memory is explicitly an alias of recall, and save_memory/save_to_synapse/store_memory all persist memories. This makes the tool boundary unclear for agents choosing between them, even though core operations like health_check and slo_report are distinct.

Naming Consistency2/5

Names are consistently snake_case, but verb usage is inconsistent: save_memory, save_to_synapse, and store_memory use different verbs for the same operation, and recall/recall_memory add an alias rather than following one convention. The pattern is readable but not predictable.

Tool Count3/5

Thirteen tools is not inherently excessive for an agent-memory/trust service, but the presence of multiple aliases inflates the surface and means not every tool earns its place. The effective set is smaller, making the count feel padded.

Completeness3/5

The surface covers initialization, save, list, search/recall, feedback, and handover, but there is no update or delete operation for memories. This leaves lifecycle management incomplete and may force agents to work around missing state-management operations.

Resources