SAGOT

policies_update

SAGOT policies.update. Uses the same authorization and validation as website, API and CLI.

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": {
      "workspaceId": "<workspaceId>",
      "revision": "<revision>",
      "policy": "<policy>"
    },
    "name": "policies_update"
  }
}

Input Schema

Name	Required	Description	Default
`policy`	Yes
`revision`	Yes
`workspaceId`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 2, 2026

changedInput schema / properties / policy / properties / disclosure / description

Previous value: -"Spoken once after the person agrees to continue, before the main conversation. Not part of the greeting."New value: +"What every call must tell the person: that they're speaking with an AI and that the call is recorded or transcribed. Agents in natural opening mode say it in their own words; agents in recorded mode play it word for word (outbound: after the person agrees to continue)."

Changed6 schema fields changedOct 18, 2026

addedInput schema / properties / policy / properties / monthlySpendLimitCentavos / anyOf

Added value: +[
+  {
+    "maximum": 10000000,
+    "minimum": 0,
+    "type": "integer"
+  },
+  {
+    "type": "null"
+  }
+]

changedInput schema / properties / policy / properties / monthlySpendLimitCentavos / default
```
Previous value: -100000New value: +null
```

changedInput schema / properties / policy / properties / monthlySpendLimitCentavos / description

Previous value: -"Most that calls on SAGOT numbers may cost from the prepaid balance per calendar month (UTC), in centavos (phase 42). A call whose maximum cost would pass it is refused."New value: +"Optional cap on what calls on SAGOT numbers may cost per calendar month (UTC), in centavos (phase 42). null (default) = no cap: the prepaid balance is the limit. When set, a call whose maximum cost would pass it is refused."

removedInput schema / properties / policy / properties / monthlySpendLimitCentavos / maximum
```
Removed value: -10000000
```
removedInput schema / properties / policy / properties / monthlySpendLimitCentavos / minimum
```
Removed value: -0
```
removedInput schema / properties / policy / properties / monthlySpendLimitCentavos / type
```
Removed value: -"integer"
```

Changed1 schema field changedOct 18, 2026

addedInput schema / properties / policy / properties / monthlySpendLimitCentavos

Added value: +{
+  "default": 100000,
+  "description": "Most that calls on SAGOT numbers may cost from the prepaid balance per calendar month (UTC), in centavos (phase 42). A call whose maximum cost would pass it is refused.",
+  "maximum": 10000000,
+  "minimum": 0,
+  "type": "integer"
+}

Changed1 schema field changedOct 17, 2026

addedInput schema / properties / policy / properties / assistantCallApproval

Added value: +{
+  "default": true,
+  "description": "Calls that a connected AI assistant (OAuth, phase 41) asks for wait until a person approves them on the website. Admins can turn this off; assistants never can.",
+  "type": "boolean"
+}

First observedOct 17, 2026

TDQS

D1.9/5.0

Behavior2/5

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

No annotations are provided, so the description must carry the full behavioral burden. It notes that authorization and validation match other interfaces, but omits mutation effects, revision/concurrency behavior, validation failures, and what happens to existing policy fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The definition is short, but the first sentence merely restates the tool name and does not front-load actionable purpose. The second sentence is the only substantive one, leaving the overall structure under-specified rather than concise.

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

Completeness2/5

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

This is a complex mutation tool with a large nested policy object, no annotations, and no output schema. The description does not explain update semantics, revision handling, or validation implications, so it is not complete enough for safe invocation despite the schema's structural detail.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description does not mention workspaceId, revision, or the nested policy object at all. With top-level schema description coverage at 0%, the description fails to compensate for undocumented parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description starts with "SAGOT policies.update," which largely restates the tool name rather than defining the operation. It does not explain what a policy is, what fields are being updated, or how this differs from the sibling policies_get tool.

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?

There is no guidance on when to use this tool versus policies_get or other workspace/configuration tools. The note about sharing authorization and validation with the website, API, and CLI does not tell an agent when or why to call policies_update.

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

All SAGOT tools Inspect

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

Need Help?