Skip to main content
Glama

PumpPill — token safety and measured outcomes

by org.pumppill
OverviewDiscussionsAdmin

Buy a Robinhood Chain token (agent trading)

agent_buy
Destructive

Buy a Robinhood Chain token with ETH from the member's PumpPill trade bot wallet. Needs the member's agent key (X-Agent-Key: ppa_..., made in PumpPill's Telegram trade bot under Settings, AI agent). PumpPill reads the token first and, unless the member turned refusal off, refuses a HIGH/CRITICAL read, a token it has not read, or a read too thin to clear (verdict unknown, contract powers unread), saying why. The member's own limits apply. The order is written down before it is placed; poll agent_order for the result. Moves real money: confirm the token and size with the member first.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ethNo
againNo
addressNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / again
      Added value: +{
+  "default": false,
+  "title": "Again",
+  "type": "boolean"
+}
  2. Added

TDQS

A4.1/5.0
Behavior5/5

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

Annotations already declare destructive/non-idempotent/open-world, and the description substantially adds: auth header format, the pre-trade safety read and refusal policy (HIGH/CRITICAL, unread, thin reads), member-level limits, the write-before-place ordering, and the real-money warning. This is rich behavioral context well beyond the structured fields.

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?

Front-loaded with the core action and funding source, then layers prerequisites, refusal behavior, and the money warning. Dense but each sentence carries operational meaning; only the nested clause about refusal conditions is a touch heavy.

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, no-output-schema trading tool, the description covers auth, safety gating, limits, order-result polling, and the real-money caution, so an agent can act correctly. The unexplained 'again' parameter is the main remaining gap.

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

Parameters2/5

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

Schema description coverage is 0% and the schema itself provides no titles beyond single words. The description implies address=token and eth=size but never says so explicitly, and the 'again' parameter is entirely unexplained in both schema and description. With three undocumented parameters, the description fails to compensate for the coverage gap.

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+resource+funding source: 'Buy a Robinhood Chain token with ETH from the member's PumpPill trade bot wallet.' It is clearly distinct from the sibling agent_sell and names the chain and wallet context an agent needs to route correctly.

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 prerequisites (the X-Agent-Key credential and where to obtain it), states the refusal conditions that gate the call, and routes the agent to 'poll agent_order for the result.' It stops short of explicitly contrasting with agent_sell or specifying when not to use this tool, so it is clear context without full exclusions.

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

All PumpPill — token safety and measured outcomes 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