Skip to main content
Glama

loophole-tape

by io.github.gosadu
OverviewDiscussionsAdmin

New pump.fun launches with rug odds ($0.001)

launches_since
Read-onlyIdempotent

$0.001 USDC per poll. Use when a bot polls for newly launched Solana tokens on pump.fun with their calibrated odds; for a one-off screen of the last hour use GET /v1/launches/recent, and for one mint the $0.005 rug check. The polling feed for bots: every covered launch created after since (unix seconds; default the last 60 s, at most the last hour), oldest first, up to 100 per call, each with creator, reserve, buys, buyer inflow, top-5 holder and creator shares, first-observed flags, the calibrated P(rug within 300 s) for young mints and P(true graduation), and the paid check URL. Returns next_cursor to pass back as since. An empty page costs the same call, so poll at the launch rate you need (about 20 launches per minute). Each item also carries its verdict word by the /v1/verdict rule with p_rug_300s and p_true_graduation; no_avoid=1 drops avoid items and min_p_grad keeps items at or above that P(true graduation), and next_cursor still advances past what they drop.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNolaunches per call
sinceNounix seconds of the last launch seen (next_cursor of the previous call); omit for the last 60 s
no_avoidNotrue or 1: leave out items whose verdict is avoid
min_p_gradNokeep items whose P(true graduation) is at least this (0 = no floor)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / min_p_grad
      Added value: +{
+  "default": 0,
+  "description": "keep items whose P(true graduation) is at least this (0 = no floor)",
+  "maximum": 1,
+  "minimum": 0,
+  "title": "Min P Grad",
+  "type": "number"
+}
    • addedInput schema / properties / no_avoid
      Added value: +{
+  "default": false,
+  "description": "true or 1: leave out items whose verdict is avoid",
+  "title": "No Avoid",
+  "type": "boolean"
+}
  2. Added

TDQS

A5/5.0
Behavior5/5

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

Annotations already mark it read-only, idempotent, and non-destructive, and the description adds rich behavioral context: per-poll cost, empty pages billed the same, at-most-one-hour window, oldest-first order, next_cursor paging, and filter behavior including next_cursor advancing past dropped items. This goes far beyond the annotation safety profile.

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?

The description is long but every clause carries operational value: price, intended use, alternatives, pagination, filtering, and output fields. It is front-loaded with the most important information and remains dense without padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description fully enumerates the response contents: creator, reserve, buys, buyer inflow, holder/creator shares, first-observed flags, calibrated probabilities, check URL, and verdict word. It also covers defaults, limits, cost, and paging, so an agent has everything needed to call it correctly.

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?

Schema coverage is 100%, so the baseline is 3, but the description adds substantial meaning: `since` is defined as the previous call's next_cursor with default and maximum range, `no_avoid` drops verdict-avoid items, and `min_p_grad` floors P(true graduation) while next_cursor still advances. These nuances are not 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: 'Use when a bot polls for newly launched Solana tokens on pump.fun with their calibrated odds.' It clearly describes the feed semantics (launches created after `since`, oldest first, up to 100 per call) and distinguishes itself from one-off screens and per-mint rug checks.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly says when to use this tool ('Use when a bot polls...') and names alternatives: 'for a one-off screen of the last hour use GET /v1/launches/recent, and for one mint the $0.005 rug check.' It also gives operational advice on polling cadence and the cost of empty pages.

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

All loophole-tape 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