SAGOT

agents_save

SAGOT agents.save. 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>",
      "id": "<id>",
      "revision": "<revision>",
      "persona": "<persona>"
    },
    "name": "agents_save"
  }
}

Input Schema

Name	Required	Description	Default
`id`	Yes
`persona`	Yes
`revision`	Yes
`workspaceId`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 2, 2026

addedInput schema / properties / persona / properties / opening

Added value: +{
+  "default": "natural",
+  "description": "How the agent opens calls (phase 47). natural: the agent says everything live; the greeting is the basis for its own opening, and it tells the person it's an AI and that the call is recorded in its own words, as part of the opening (or a moment later if they're in a hurry or need help right away). recorded: the greeting and the policy disclosure are played as recordings, word for word.",
+  "enum": [
+    "natural",
+    "recorded"
+  ],
+  "type": "string"
+}

First observedOct 17, 2026

TDQS

D1.9/5.0

Behavior2/5

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

With no annotations, the description carries the full burden, yet it never states that this is a mutating write, that it requires an optimistic-concurrency revision, or what happens on revision conflict. "Same authorization and validation as website, API and CLI" is the sole behavioral hint and is too abstract to be actionable.

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

Conciseness3/5

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

It is short and not bloated, but the lead sentence is a waste (tool name restated) and the useful content is a single vague sentence. Front-loading is poor because the first thing the agent reads carries no information.

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

Completeness1/5

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

This is a mutation tool with a deeply nested persona schema, four required params including a concurrency revision, no output schema, and no annotations — the description supplies none of the missing context an agent would need to call it correctly.

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?

Schema description coverage is 0% and the description mentions none of the four required parameters. The critical semantics of `revision` (concurrency check) and the nested `persona` object are entirely unexplained, so the description compensates for nothing.

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?

"SAGOT agents.save" simply restates the tool name and does not say what saving an agent actually does (create vs. update an existing persona, what gets persisted). It offers no differentiation from siblings like agents_create, agents_publish, or agents_rollback.

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 indication of when to use this tool versus agents_create or agents_publish, nor any prerequisites such as needing an existing agent id and current revision. The only guidance is an analogy to other interfaces, which doesn't help an agent choose this tool.

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?