Skip to main content
Glama

router_change

Destructive

Change router or modem web UI settings by setting, adding, or deleting objects, with a preview before confirming changes.

Instructions

Change any setting the web UI can change. action: "set" (stack = the row's _stack; omit for single objects), "add" (parent_stack = the parent row's _stack, e.g. "1" for LAN_DHCP_STATIC_ADDR under LAN 1) or "delete". Read the object first so attribute names match. Without confirm=true it only shows what it would do.

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": {
      "action": "<action>",
      "object": "<object>"
    },
    "name": "router_change"
  }
}

Input Schema

NameRequiredDescriptionDefault
stackNo
actionYes
objectYes
confirmNo
attributesNo
parent_stackNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the write risk is known. The description adds genuinely useful context beyond that: the default is a dry-run unless confirm=true, and a delete action exists. It does not say what a delete destroys or how partial attribute sets affect existing settings, so it exceeds but does not richly cover the behavioral bar for a destructive tool.

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

Conciseness4/5

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

Dense and front-loaded: purpose first, then per-action parameter semantics, then the safety note. Fits a lot into three sentences, though the compressed phrasing ('stack = the row's _stack') and embedded quoting make it slightly harder to parse than necessary.

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 destructive multi-action mutation tool with no output schema and zero schema annotations, the description covers purpose, action modes, required stack addressing, dry-run default, and the read-before-write prerequisite. Remaining gaps (return payload, error behavior, what delete erases) are real but secondary for a 6-parameter 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 0% across 6 parameters, so the description carries the burden and does explain action values (set/add/delete), the stack and parent_stack distinction with a concrete example, and confirm's dry-run semantics. However, 'attributes' and 'object' receive only indirect treatment ('attribute names match'), and no format or typing guidance is given for the attribute map, so compensation is partial.

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

Purpose4/5

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

States a specific verb+resource: 'Change any setting the web UI can change', and immediately disambiguates the write role against read-oriented siblings like router_read and router_objects. The scope ('any setting the web UI can change') is broad but concrete enough for an agent to know this is the mutation entry point.

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 real operational guidance: read the object first so attribute names match (implying router_read/router_objects before acting), and explains that without confirm=true it only previews. It stops short of naming the specific sibling read tool or stating when to avoid using this versus router_run.

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