Skip to main content
Glama

set_rules

Replace the workspace's rules (start from get_rules). They act on tickets that arrive from now on; what a rule does is shown in the ticket as done by the system. The away message needs working hours (set_reply_times). Owner or admin; Pro and higher.

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": {
      "hand_out": "<hand_out>",
      "hand_out_to_user_ids": "<hand_out_to_user_ids>",
      "tag_rules": "<tag_rules>",
      "away": "<away>",
      "away_message": "<away_message>"
    },
    "name": "set_rules"
  }
}

Input Schema

NameRequiredDescriptionDefault
awayYesTell visitors who write outside working hours (set with set_reply_times): true to switch it on.
hand_outYesHand new live tickets out in turn: true to switch it on.
tag_rulesYesTags added when a ticket arrives, from what its form was answered with. This replaces the list.
away_messageYesWhat they are told, up to 500 characters. Shown as text under "sent"; never mailed.
hand_out_limitsNoThe most open tickets each of them holds at once (1 to 500), by id from list_teammates; someone left out takes any number. Leave this out to keep the numbers as they are.
close_after_daysNoClose a ticket that has waited on the customer this many days (3 to 90). Leave out to never close them.
hand_out_when_roomNoA ticket that found everyone full, once someone has room: "auto" hands it out by itself, "button" waits for an owner or admin to press Hand out. Leave this out to keep it as it is.
hand_out_to_user_idsYesThe people tickets are handed to in turn: ids from list_teammates.
hand_out_counts_waitingNoWhether a person's number counts the tickets they hold that wait on the customer too, not only the open ones. Leave this out to keep it as it is.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / close_after_days / type
      Previous value: -[
      -  "integer",
      -  "null"
      -]New value: +"integer"
    • changedInput schema / properties / hand_out_counts_waiting / type
      Previous value: -[
      -  "boolean",
      -  "null"
      -]New value: +"boolean"
    • changedInput schema / properties / hand_out_limits / type
      Previous value: -[
      -  "object",
      -  "null"
      -]New value: +"object"
    • changedInput schema / properties / hand_out_when_room / type
      Previous value: -[
      -  "string",
      -  "null"
      -]New value: +"string"
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Adds real behavior beyond the annotations: rules only affect tickets arriving from now on, and rule actions surface in the ticket as system-done. That forward-only scope and audit visibility are not derivable from readOnlyHint=false/destructiveHint=false, and the auth/plan gate is stated. It does not carry a contradiction, though the full-replace semantics (existing rules not resubmitted are lost) sits in tension with a non-destructive hint and could be stated more bluntly.

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 short sentences, front-loaded with the action and its read-first dependency. Every clause carries information: replace semantics, effect timing, audit visibility, prerequisite, permissions. No filler.

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 nine-parameter mutation with a nested object and no output schema, the description covers what the tool replaces, when the rules take effect, prerequisites, and access gating. Remaining gaps (partial-update behavior, response shape) are largely covered by the fully documented schema.

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 all nine parameters in detail. The description adds only one cross-reference beyond that (away_message depends on working hours from set_reply_times), so the prescribed baseline of 3 applies.

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 ("Replace the workspace's rules") and immediately anchors it against the sibling that reads the same object ("start from get_rules"). An agent can distinguish set_rules from get_rules without opening either 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?

"Start from get_rules" gives the read-then-write pattern, and "The away message needs working hours (set_reply_times)" names a prerequisite plus the sibling that satisfies it. It lacks explicit when-not-to-use guidance, but permissions ("Owner or admin; Pro and higher") are spelled out.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources