Sautikit

upsert_agent_tool

Idempotent

Create or update an agent HTTP tool by tool_id (mint a fresh UUID to create; reuse an id from list_agent_tools to update). headers are WRITE-ONLY: values are stored encrypted and never echoed back, so secrets cannot round-trip into a conversation.

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": {
      "agent_id": "<agent_id>",
      "tool_id": "<tool_id>",
      "name": "<name>",
      "description": "<description>",
      "url": "<url>"
    },
    "name": "upsert_agent_tool"
  }
}

Input Schema

Name	Required	Description
`url`	Yes	HTTPS endpoint invoked at call time
`name`	Yes	tool name the agent calls, e.g. crm_lookup
`method`	No	HTTP method (default POST)
`headers`	No	request headers incl. secrets — WRITE-ONLY, values are never returned by any read
`purpose`	No	Required on tools that read data or reports; recommended on every tool. One sentence: what you are doing and why (for example "finding this caller's open ticket to answer them"). Building a report, dashboard, analytics or an export is a SautiDesk Pro feature done by the report tools, not by pulling records.
`tool_id`	Yes	tool UUID: reuse an id from list_agent_tools to update, or mint a fresh UUID to create
`agent_id`	Yes	agent UUID
`parameters`	No	JSON Schema for the tool's arguments
`timeout_ms`	No	invocation timeout in milliseconds
`body_params`	No	static body fields merged into every invocation
`description`	Yes	what the tool does (the agent model reads this)

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Goes beyond the annotations (idempotentHint, destructiveHint=false, openWorldHint=false) by disclosing that header values are stored encrypted and never echoed back, which matters for secret handling. It omits update semantics such as whether omitted fields are cleared or preserved, which is the main behavioral risk for an upsert.

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?

Two sentences, zero filler, with the create/update discriminator front-loaded and the security caveat placed second where it matters most. Nothing is redundant or buried.

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?

Adequate for an 11-parameter nested-object tool with no output schema: the schema documents every field at full coverage, and the description supplies the upsert discriminator and the secret-handling caveat. The remaining gap is update-side semantics (partial vs full replacement), which an agent would want before mutating an existing tool.

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%, including tool_id's create-vs-update note and headers' write-only note, so the description largely restates what the schema already documents. Baseline 3 applies; it adds no syntax, format, or interaction detail beyond the structured fields.

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?

Names a specific verb pair and resource (create/update an agent HTTP tool) and immediately disambiguates the two modes by tying them to tool_id semantics. An agent can distinguish this from delete_agent_tool and list_agent_tools without opening any 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 states how to select create vs update and names list_agent_tools as the source of an existing id, which is actionable routing guidance. It does not cover when not to use this tool or point to delete_agent_tool for removal, so it falls short of the full when/when-not/alternatives bar.

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

All Sautikit 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?