Skip to main content
Glama
Coinversaa

Coinversaa Pulse

Official
by Coinversaa
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Cohort Bias History

pulse_cohort_bias_history
Read-onlyIdempotent

Track how trader cohorts shift their long/short positioning over time using hourly bias snapshots per coin or globally, covering up to 30 days of history.

Instructions

Get historical hourly bias snapshots for trader cohorts. Returns net long/short notional and account counts per tier — 32 tier rows per hour (16 PnL + 16 size tiers), so filter with tierType and/or tier for a readable series. Use this to see how different groups (whales, smart money) have shifted their positioning over time. Supports per-coin or global aggregate; the API default window is 7d, max 30d. Returns { rows, totalCount, truncated, note? } with rows newest first, capped at limit (default 100); when truncated, narrow with tierType/tier or a shorter since, or raise limit (max 2000). Cohort history is served for up to the last 30 days; see data_coverage.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
coinNoFilter by coin symbol (e.g. BTC, ETH, SOL). For builder dex: prefix:COIN (e.g. xyz:SILVER). Omit for global exchange aggregate.
tierNoKeep only one tier's rows (either vocabulary). Combine with tierType for a single series.
limitNoMax rows to return, newest first (default 100, max 2000).
sinceNoTime window for history (max 30d). e.g. '24h', '7d', '30d'
endTimeNoExplicit end time (ISO string or timestamp). Defaults to now.
tierTypeNoKeep only PnL-tier or size-tier rows (applied by the connector; halves the row count).
startTimeNoExplicit start time (ISO string or timestamp). Overrides 'since'.
useToonFormatNoReturn data in compact toon format (default: true). Set to false for standard JSON.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.12.0
    • addedInput schema / properties / limit
      Added value: +{
+  "default": 100,
+  "description": "Max rows to return, newest first (default 100, max 2000).",
+  "maximum": 2000,
+  "minimum": 1,
+  "type": "integer"
+}
    • addedInput schema / properties / tier
      Added value: +{
+  "description": "Keep only one tier's rows (either vocabulary). Combine with tierType for a single series.",
+  "enum": [
+    "apex",
+    "sharps",
+    "grinders",
+    "scrapers",
+    "crowd",
+    "bleeders",
+    "trapped",
+    "blown_out",
+    "heavyweights",
+    "cruiserweights",
+    "middleweights",
+    "welterweights",
+    "lightweights",
+    "featherweights",
+    "flyweights",
+    "strawweights",
+    "money_printer",
+    "smart_money",
+    "grinder",
+    "humble_earner",
+    "exit_liquidity",
+    "semi_rekt",
+    "full_rekt",
+    "giga_rekt",
+    "leviathan",
+    "tidal_whale",
+    "whale",
+    "small_whale",
+    "apex_predator",
+    "dolphin",
+    "fish",
+    "shrimp"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / tierType
      Added value: +{
+  "description": "Keep only PnL-tier or size-tier rows (applied by the connector; halves the row count).",
+  "enum": [
+    "pnl",
+    "size"
+  ],
+  "type": "string"
+}
  2. Addedv0.6.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already establish the safe-read profile (readOnlyHint, idempotentHint, destructiveHint=false), and the description adds substantial context on top: hourly granularity, 32 rows per hour, default 7d window and 30d ceiling, row cap of 100 with max 2000, and truncation behavior. It stops short of explaining rate limits or latency characteristics.

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 paragraph front-loads what the tool returns, then moves to filtering, scope, and return shape in a logical order. It is dense and mostly earns its sentences, though the limit default/max and the truncation remediation repeat information already in the schema.

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 still specifies the return envelope ({rows, totalCount, truncated, note?}), ordering (newest first), the cap and how to relieve truncation, the time window limits, and a pointer to data_coverage. An agent can call and handle results correctly without further information.

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 every parameter's type, enum, default, and bounds. The description mostly restates those facts (limit default/max, since window, tierType/tier filtering) rather than adding new syntax or format meaning beyond the domain note about 16 PnL + 16 size tiers, so the baseline 3 applies.

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 precise verb and resource — historical hourly bias snapshots for trader cohorts — and specifies the exact payload (net long/short notional and account counts per tier). 'Historical' implicitly separates it from the live_cohort_bias sibling, but no sibling is named, so the agent gets no explicit routing help against live_cohort_bias_history or pulse_cohort_history.

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 a clear use case ('see how different groups have shifted their positioning over time') plus concrete operational guidance on narrowing results via tierType/tier or a shorter since. It lacks explicit when-not-to-use conditions and never names an alternative tool for the live/snapshot case.

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

Deploy Server

Other Tools