Seiche — world-markets evidence terminal

by io.github.beepboop2025

Institutional USD money-market desk

money_market_context

Read-onlyIdempotent

Granular, descriptive USD money-market context from the already assembled desk: policy corridor and overnight spreads; SOFR/TGCR/BGCR distributions and tails; repo-segment rates and volumes; CP-Treasury spreads; bills and cash curve; liquidity buffers and Fed facilities; and MMF repo plumbing. Use optional section to request a compact summary, one named desk section, diagnostics, sources, methodology, or all context. Diagnostics count funding persistence, compare secured/unsecured benchmarks and show calendar cohorts with sample limits, without changing any score. Returns exact-date alignment, native-cadence changes, empirical own-history statistics, freshness, coverage, formulas, sources, and caveats as applicable. Chart history is always omitted. Reads only an already completed cached or persisted snapshot; it never triggers collection or engine recomputation, while freshness is re-evaluated at response time. Context only: no causal, predictive, probability, or trade claim.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`section`	No	Projection to return; defaults to the compact desk summary.	summary

Output Schema

TableJSON Schema

Name	Required	Description	Default
`ok`	No
`asof`	No
`reason`	No
`regime`	No
`schema`	No
`status`	No
`caveats`	No
`sources`	No
`category`	No
`coverage`	No
`formulas`	No
`sections`	No
`freshness`	No
`selection`	No
`quant_read`	No
`countercase`	No
`diagnostics`	No
`methodology`	No
`context_only`	No
`legal_notices`	No
`plain_language`	No
`section_catalog`	No
`source_metadata`	No
`strongest_signal`	No
`available_selectors`	No
`snapshot_generated_at`	No
`chart_history_included`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedSep 5, 2026

changedInput schema / properties / section / enum

Previous value: -[
-  "summary",
-  "policy_corridor",
-  "secured_distributions",
-  "repo_segments",
-  "unsecured_funding",
-  "bills_cash_curve",
-  "liquidity_buffers",
-  "mmf_plumbing",
-  "sources",
-  "methodology",
-  "all"
-]New value: +[
+  "summary",
+  "diagnostics",
+  "policy_corridor",
+  "secured_distributions",
+  "repo_segments",
+  "unsecured_funding",
+  "bills_cash_curve",
+  "liquidity_buffers",
+  "mmf_plumbing",
+  "sources",
+  "methodology",
+  "all"
+]

changedOutput schema / properties / available_selectors / items / enum

Previous value: -[
-  "summary",
-  "policy_corridor",
-  "secured_distributions",
-  "repo_segments",
-  "unsecured_funding",
-  "bills_cash_curve",
-  "liquidity_buffers",
-  "mmf_plumbing",
-  "sources",
-  "methodology",
-  "all"
-]New value: +[
+  "summary",
+  "diagnostics",
+  "policy_corridor",
+  "secured_distributions",
+  "repo_segments",
+  "unsecured_funding",
+  "bills_cash_curve",
+  "liquidity_buffers",
+  "mmf_plumbing",
+  "sources",
+  "methodology",
+  "all"
+]

addedOutput schema / properties / diagnostics
```
Added value: +{
+  "type": "object"
+}
```

changedOutput schema / properties / selection / enum

Previous value: -[
-  "summary",
-  "policy_corridor",
-  "secured_distributions",
-  "repo_segments",
-  "unsecured_funding",
-  "bills_cash_curve",
-  "liquidity_buffers",
-  "mmf_plumbing",
-  "sources",
-  "methodology",
-  "all"
-]New value: +[
+  "summary",
+  "diagnostics",
+  "policy_corridor",
+  "secured_distributions",
+  "repo_segments",
+  "unsecured_funding",
+  "bills_cash_curve",
+  "liquidity_buffers",
+  "mmf_plumbing",
+  "sources",
+  "methodology",
+  "all"
+]

Changed1 schema field changedAug 21, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": true,
+  "anyOf": [
+    {
+      "properties": {
+        "chart_history_included": {
+          "const": false
+        },
+        "context_only": {
+          "const": true
+        },
+        "schema": {
+          "const": "seiche.money-market-desk.v1"
+        }
+      },
+      "required": [
+        "ok",
+        "schema",
+        "context_only",
+        "selection",
+        "chart_history_included",
+        "caveats",
+        "section_catalog",
+        "available_selectors"
+      ]
+    },
+    {
+      "properties": {
+        "ok": {
+          "const": false
+        },
+        "status": {
+          "const": "FAILED"
+        }
+      },
+      "required": [
+        "ok",
+        "status",
+        "category",
+        "reason"
+      ]
+    }
+  ],
+  "description": "Chartless USD money-market desk envelope for every supported selector.",
+  "properties": {
+    "asof": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "available_selectors": {
+      "items": {
+        "enum": [
+          "summary",
+          "policy_corridor",
+          "secured_distributions",
+          "repo_segments",
+          "unsecured_funding",
+          "bills_cash_curve",
+          "liquidity_buffers",
+          "mmf_plumbing",
+          "sources",
+          "methodology",
+          "all"
+        ],
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "category": {
+      "type": "string"
+    },
+    "caveats": {
+      "type": "array"
+    },
+    "chart_history_included": {
+      "type": "boolean"
+    },
+    "context_only": {
+      "type": "boolean"
+    },
+    "countercase": {
+      "type": [
+        "object",
+        "null"
+      ]
+    },
+    "coverage": {
+      "type": [
+        "object",
+        "null"
+      ]
+    },
+    "formulas": {
+      "type": "array"
+    },
+    "freshness": {
+      "type": [
+        "object",
+        "null"
+      ]
+    },
+    "legal_notices": {
+      "type": "array"
+    },
+    "methodology": {
+      "type": "object"
+    },
+    "ok": {
+      "type": "boolean"
+    },
+    "plain_language": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "quant_read": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "reason": {
+      "type": "string"
+    },
+    "regime": {
+      "type": [
+        "object",
+        "null"
+      ]
+    },
+    "schema": {
+      "type": "string"
+    },
+    "section_catalog": {
+      "type": "array"
+    },
+    "sections": {
+      "type": "array"
+    },
+    "selection": {
+      "enum": [
+        "summary",
+        "policy_corridor",
+        "secured_distributions",
+        "repo_segments",
+        "unsecured_funding",
+        "bills_cash_curve",
+        "liquidity_buffers",
+        "mmf_plumbing",
+        "sources",
+        "methodology",
+        "all"
+      ],
+      "type": "string"
+    },
+    "snapshot_generated_at": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "source_metadata": {
+      "type": "array"
+    },
+    "sources": {
+      "type": "array"
+    },
+    "status": {
+      "type": "string"
+    },
+    "strongest_signal": {
+      "type": [
+        "object",
+        "null"
+      ]
+    }
+  },
+  "type": "object"
+}

AddedAug 21, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond the readOnly/idempotent annotations, the description discloses substantial behavioral detail: it never triggers collection or recomputation, freshness is re-evaluated at response time, chart history is always omitted, diagnostics do not change any score, and only a cached or persisted snapshot is accessed. There is no contradiction with annotations.

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 description is long but every sentence adds information: data scope, section usage, diagnostics semantics, return contents, chart omission, snapshot behavior, and limitations. It is front-loaded with the purpose and list of content, though a few phrases overlap ('already assembled desk' vs. 'already completed cached or persisted snapshot').

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?

For a tool with one optional enum parameter, read-only annotations, and an output schema, the description is complete: it covers what data is returned, how to select projections, what diagnostics do, freshness behavior, chart omission, and non-claims. An agent has enough detail to invoke it correctly and understand its limitations.

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

Parameters4/5

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

With only one optional parameter and 100% schema coverage, the schema already documents `section`. The description adds useful semantics by explaining that `section` can request a compact summary, a named desk section, diagnostics, sources, methodology, or all context, and mentions the default behavior implicitly.

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-resource purpose: it 'returns' granular descriptive USD money-market context from the 'already assembled desk,' and enumerates the exact data domains (SOFR/TGCR/BGCR, repo, CP-Treasury, bills/cash, Fed facilities, MMF plumbing). It also distinguishes itself from scoring/forecasting siblings by explicitly saying 'Context only: no causal, predictive, probability, or trade claim.'

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 description gives clear context for when to call it: to read a completed cached or persisted snapshot, request 'context only,' and never trigger computation or engine recomputation. It explicitly excludes causal, predictive, probability, and trade uses, and explains that diagnostics do not change any score, but it does not name sibling tools as alternatives.

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

All Seiche — world-markets evidence terminal 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.