AlphaYou: Smart Money Intel

Inspect position changes

get_hyperliquid_activity

Read-only

Use for observed position changes over one to 168 hours in the watcher cohort. Returns one oldest-first page, with since and next_cursor for continuation. The default minimum position notional is $1 million; pass 0 for all or smaller positions. Minimum notional is position size, not incremental trade amount. Polling and event-writer health are included when available. Not alerts or an exhaustive live trade feed.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_hyperliquid_activity"
  }
}

Input Schema

Name	Required	Description
`coin`	No	Exact market symbol, like BTC or xyz:NVDA
`event`	No	Only this type of position change
`hours`	No	Look-back window in hours, 1 to 168
`limit`	No	Events per page, 1 to 100
`since`	No	For continuation, pass the previous result since unchanged to keep the window fixed.
`cursor`	No	Page marker returned as next_cursor by an earlier page
`address`	No	Public wallet address, 0x plus 40 characters
`min_position_notional_usd`	No	Smallest position size in USD; 0 for all

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 13, 2026

changedInput schema / properties / cursor / description

Previous value: -"Continuation cursor; use next_cursor from the last page"New value: +"Page marker returned as next_cursor by an earlier page"

Changed7 schema fields changedNov 12, 2026
- addedInput schema / properties / address / description
```
Added value: +"Public wallet address, 0x plus 40 characters"
```
- addedInput schema / properties / coin / description
```
Added value: +"Exact market symbol, like BTC or xyz:NVDA"
```
- addedInput schema / properties / cursor / description
```
Added value: +"Continuation cursor; use next_cursor from the last page"
```
- addedInput schema / properties / event / description
```
Added value: +"Only this type of position change"
```
- addedInput schema / properties / hours / description
```
Added value: +"Look-back window in hours, 1 to 168"
```
- addedInput schema / properties / limit / description
```
Added value: +"Events per page, 1 to 100"
```
- addedInput schema / properties / min_position_notional_usd / description
```
Added value: +"Smallest position size in USD; 0 for all"
```
First observedOct 11, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Annotations only declare it is a safe, open-world read; the description goes well beyond that by disclosing pagination shape (one oldest-first page, continuation via since + next_cursor), the $1M default threshold, coverage boundaries (watcher cohort only, not exhaustive), and that polling/event-writer health is appended when available. These are exactly the traits an agent cannot infer from the annotations or schema.

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?

Six short sentences, each carrying a distinct fact, with the usage cue front-loaded and the exclusion last. It is dense but every sentence earns its place; only the pagination sentence partly overlaps with the schema descriptions for since and cursor.

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?

With no output schema, the description must carry the return-shape burden, and it does: page ordering, continuation fields, and health payloads are all stated. It stops short of describing what a single event record contains or how the watcher cohort is defined, which leaves a small gap for an 8-parameter list 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 coverage is 100%, so the schema already documents all 8 parameters, which sets the baseline at 3. The description does add real meaning on one parameter by clarifying that the $1M default is minimum *position size, not incremental trade amount* and that 0 disables the filter, but the other seven parameters get no narrative elaboration.

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?

"Use for observed position changes over one to 168 hours in the watcher cohort" names a specific resource (position change events) plus an explicit time scope and population. It closes with "Not alerts or an exhaustive live trade feed," which rules out adjacent interpretations, but it never names a specific sibling tool (e.g. get_hyperliquid_wallet_positions) it should be preferred over.

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?

The opening "Use for..." clause gives a clear positive selection condition, and the trailing "Not alerts or an exhaustive live trade feed" gives a negative one. What's missing is a pointer to the alternative when an agent does want alerts or a live feed, so the routing is directional but not complete.

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

All AlphaYou: Smart Money Intel tools Inspect

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

Need Help?