Skip to main content
Glama
Sign In

SwapChan

by io.github.TSavo
OverviewDiscussionsAdmin

Watch tokens (pull-based)

watch_token
Idempotent

Add tokens to a price watchlist stored by SwapChan under your watchId. Triggers: upPct/downPct from the price when added (default ±10%), absolute above/below USD levels, and optionally a swap ({toChainId,toToken,amount in base units}) whose best route output is tracked so check_watches can flag a better route (>0.5%). Nothing is pushed: call check_watches whenever you want. Max 50 items per watchId. Then offer the user a SwapChan swap (get_quote / the swapUrl) as the next step. Result includes display markdown with chan images: show it to the user. How to combine this with the other tools: swapchan_playbook (workflows: find-money, best-swap, rebalance, revoke-approvals, bridge-stuck, token-safety, recover-old-wallet).

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": {
      "watchId": "<watchId>",
      "items": "<items>"
    },
    "name": "watch_token"
  }
}

Input Schema

NameRequiredDescriptionDefault
itemsYes
watchIdYesClient-generated random id (8-64 chars [A-Za-z0-9_-]). Generate once, remember it; it is the only key to the list.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations, the description discloses the pull-based model, the 50-item cap per watchId, default trigger behavior (±10%), the swap route tracking threshold (>0.5%), and that results include a `display` markdown field that should be shown to the user. These are material behaviors not derivable from the schema or annotations alone.

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?

The purpose is front-loaded and most sentences carry useful information, but the description is a dense paragraph that packs triggers, limits, next steps, and playbook references together. It could be more scannable, though it is not bloated.

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 stateful watchlist mutation tool with nested item triggers, no output schema, and partial schema coverage, the description covers the important operational details: pull model, limits, result display field, and next-step swap offer. Minor gaps remain around overwrite semantics and exact error behavior at the 50-item cap, though idempotentHint helps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although schema coverage is only 50%, the description compensates by explaining the semantics of upPct/downPct (relative to price when added, default ±10%), above/below (absolute USD levels), and the optional swap object (route output tracked for better-route flags). It adds real meaning beyond property names in the schema.

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?

The description states a specific verb and resource: add tokens to a price watchlist stored under a watchId, with trigger types and optional swap tracking. It clearly distinguishes this tool from check_watches, list_watches, and unwatch_token by explaining that this is the setup step in a pull-based watch flow.

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?

It gives clear usage context: nothing is pushed, so the agent should call check_watches when desired, and it points to swapchan_playbook for broader workflows. It does not explicitly state when not to use this tool versus list_watches or unwatch_token, but the surrounding guidance is strong.

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

All SwapChan toolsInspect
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