Sautikit

set_agent_links

Idempotent

FULL-REPLACE an agent's specialist-transfer links (send every link to keep — this is PUT, not PATCH; an empty/omitted links list clears them all). target_agent_id must be another agent in this workspace: fails with agents.self_link, agents.link_target_not_found, or agents.duplicate_link_target.

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>",
      "links": "<links>"
    },
    "name": "set_agent_links"
  }
}

Input Schema

Name	Required	Description
`links`	Yes	full-replacement set of specialist-transfer links, in try order
`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.
`agent_id`	Yes	agent UUID

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 well beyond the annotations by disclosing the destructive edge case (an empty list wipes all existing links), the full-replacement contract, and the three specific error codes an agent may hit. Missing only auth/permission context and confirmation of what a successful call returns; the clear-links behavior is not contradicted by idempotentHint since PUT replacement is inherently idempotent.

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 in a single dense paragraph with the most consequential fact ('FULL-REPLACE', 'PUT, not PATCH') front-loaded and capitalized for salience. No filler, no repetition of the schema.

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?

For a mutation tool with no output schema, the description covers replacement semantics, the clearing edge case, cross-field validation, and error codes. The remaining gap is minor: no success/return behavior and no indication of prerequisite scopes or permissions.

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 coverage is 100%, so parameter meanings are already documented, giving a baseline of 3. The description adds the omitted-list-clears behavior and ties the validation constraint and error codes to target_agent_id, but says nothing about the purpose field.

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?

States a specific verb and resource — 'FULL-REPLACE an agent's specialist-transfer links' — and immediately contrasts it with the sibling read tool by declaring the write semantics (PUT, not PATCH). An agent can distinguish this from get_agent_links and update_agent without opening a 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?

Gives concrete usage conditions: send every link to keep, an empty or omitted list clears them all, and the target must be another agent in the workspace. It stops short of explicitly naming sibling alternatives (get_agent_links for reading, update_agent for other fields), so it is strong but not fully routing.

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?