Sutra

Write Sutra observation

write_observation

Save one durable memory only after the user clearly asks or agrees to save it.

Use for stable preferences, decisions, corrections, working patterns, or project facts. Do not store inferred traits, secrets, transient conversation, or information the user did not authorize Sutra to retain.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`tags`	No	Optional search tags; at most 10 tags, each no longer than 30 characters.
`cluster`	No	Destination cluster name using letters, numbers, or hyphens.	general
`content`	Yes	The preference, decision, correction, working pattern, or project fact to remember.
`importance`	No	Memory importance from 1 (low) to 5 (critical); use 3 by default.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`status`	Yes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed12 schema fields changedSep 2, 2026

addedInput schema / properties / cluster / description

Added value: +"Destination cluster name using letters, numbers, or hyphens."

addedInput schema / properties / cluster / maxLength
```
Added value: +50
```
addedInput schema / properties / cluster / minLength
```
Added value: +1
```
addedInput schema / properties / cluster / pattern
```
Added value: +"^[A-Za-z0-9-]{1,50}$"
```

addedInput schema / properties / content / description

Added value: +"The preference, decision, correction, working pattern, or project fact to remember."

addedInput schema / properties / content / maxLength
```
Added value: +2000
```
addedInput schema / properties / content / minLength
```
Added value: +1
```

addedInput schema / properties / importance / description

Added value: +"Memory importance from 1 (low) to 5 (critical); use 3 by default."

addedInput schema / properties / tags / description

Added value: +"Optional search tags; at most 10 tags, each no longer than 30 characters."

removedOutput schema / additionalProperties
```
Removed value: -true
```

addedOutput schema / properties

Added value: +{
+  "status": {
+    "enum": [
+      "saved",
+      "duplicate"
+    ],
+    "type": "string"
+  }
+}

addedOutput schema / required
```
Added value: +[
+  "status"
+]
```

First observedSep 2, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations only indicate a non-read, non-idempotent, non-destructive write. The description adds meaningful behavior: it saves durable memory only after explicit user agreement and defines what must not be retained. This is substantive disclosure beyond the structured annotations.

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 sentences with the most important constraint front-loaded and no wasted words. The consent requirement, content scope, and exclusions each have their own sentence, making it easy for an agent to parse.

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

Completeness5/5

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

For a four-parameter write tool with a rich input schema and output schema, the description covers the essential policy and safety context needed to invoke it correctly. It does not need to explain return values because the output schema exists.

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 already documents content length, tags limits, cluster pattern, and importance range. The description mostly repeats the content categories already in the schema and adds little parameter-level detail.

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?

The description opens with a precise action — save one durable memory — and clearly ties it to user consent. It lists concrete content categories (preferences, decisions, corrections, working patterns, project facts), and the write semantics distinguish it from the read/export sibling tools.

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?

It gives explicit positive use cases and even clearer negative cases (no inferred traits, secrets, transient conversation, unauthorized information), plus the consent precondition. It does not name a read/search sibling as the alternative when the desired information should not be stored, so the routing guidance is not fully explicit.

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

All Sutra tools Inspect

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

A4.4/5.0

Disambiguation5/5

Each tool has a clearly scoped purpose, and the descriptions include explicit usage rules that prevent overlap. Memory retrieval is split into read_context, search_memory, get_cluster, and export_all with distinct trigger conditions, so agents can reliably choose the right tool.

Naming Consistency5/5

All tools use a consistent lower_snake_case verb_noun pattern such as list_clusters, get_skill, search_memory, write_observation, and upload_skill. The naming is predictable and uniform across the entire set.

Tool Count5/5

Ten tools is well-scoped for a personal memory and skills server: it covers memory access, skill access, discovery, writing observations, and export. Each tool earns its place without the set feeling bloated or thin.

Completeness3/5

The server covers discovery, retrieval, saving observations, and uploading skills, but it lacks update/delete operations for memories and skill management beyond upload. This leaves a notable lifecycle gap: incorrect or obsolete saved observations cannot be removed or corrected in place.

Resources

Need Help?