Seiche — world-markets evidence terminal

by io.github.beepboop2025

Cache-only Seiche context for trade-safety guards

trade_safety_risk_context

Read-onlyIdempotent

A deterministic, bounded projection of the last completed Seiche board: funding regime, 0-100 stress index, coverage, source staleness counts, snapshot clock, and conservative evidence clock. It repeats the rights check and never collects, fits, calls a network source, reads a notary ledger, or contacts a broker. This is metadata-only derived context, not order-bound, non-executable, never real-money eligible, and it does not evaluate stream attestations or treat them as per-order authority.

Input Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Output Schema

TableJSON Schema

Name	Required	Description	Default
`ok`	No
`state`	No
`clocks`	No
`reason`	No
`regime`	No
`schema`	No
`status`	No
`category`	No
`staleness`	No
`disclaimer`	No
`executable`	No
`source_url`	No
`attestation`	No
`fault_count`	No
`limitations`	No
`context_only`	No
`coverage_pct`	No
`stress_index`	No
`rights_status`	No
`evidence_class`	No
`projection_mode`	No
`canonicalization`	No
`executable_quote`	No
`attestation_state`	No
`projection_sha256`	No
`can_authorize_order`	No
`real_money_eligible`	No
`request_time_broker`	No
`request_time_notary`	No
`request_time_network`	No
`request_time_collection`	No
`source_snapshot_version`	No
`request_time_model_fitting`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 1, 2026

addedOutput schema / properties / clocks / properties / all_provenance_as_of
```
Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}
```

addedOutput schema / properties / clocks / properties / retired_sources

Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "as_of": {
+        "type": "string"
+      },
+      "last_observation": {
+        "type": "string"
+      },
+      "mnemonic": {
+        "type": "string"
+      },
+      "replacement": {
+        "type": "string"
+      },
+      "retired_from": {
+        "type": "string"
+      },
+      "source": {
+        "type": "string"
+      },
+      "source_url": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "source",
+      "mnemonic",
+      "as_of",
+      "last_observation",
+      "retired_from",
+      "replacement",
+      "source_url"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

changedOutput schema / properties / clocks / required

Previous value: -[
-  "snapshot_generated_at",
-  "evidence_as_of",
-  "evaluated_at",
-  "snapshot_age_seconds",
-  "evidence_age_seconds",
-  "basis"
-]New value: +[
+  "snapshot_generated_at",
+  "evidence_as_of",
+  "evaluated_at",
+  "snapshot_age_seconds",
+  "evidence_age_seconds",
+  "all_provenance_as_of",
+  "retired_sources",
+  "basis"
+]

AddedSep 2, 2026

TDQS

A3.5/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint=false, idempotentHint, and destructiveHint=false, but the description adds substantial context beyond that: it names what the tool does NOT do (no collection, no fitting, no network, no notary ledger, no broker contact) and characterizes output as metadata-only, non-executable, non-real-money. This is meaningful disclosure of side-effect boundaries and freshness/clock semantics.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two well-structured sentences, but heavily front-loaded with jargon and contains redundant negation sequences ('never collects, fits, calls a network source, reads a notary ledger, or contacts a broker' plus a second list of non-goals). Some clauses could be consolidated without loss.

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 zero-param, cache-only context tool with an output schema, the description adequately covers what the tool returns and its operational boundaries. It doesn't explain how downstream 'trade-safety guards' should consume the output or the meaning of the evidence clock, but the output schema can carry field-level detail.

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?

Zero parameters, so baseline 4. Schema coverage is 100% and additionalProperties=false, so nothing further is required; description correctly focuses on output semantics rather than params.

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 specific verb+resource: a 'deterministic, bounded projection of the last completed Seiche board' that returns funding regime, stress index, coverage, staleness counts, and clocks. Clear and differentiated from siblings like funding_stress_now (live now) by the 'last completed board' framing. The jargon ('Seiche board', 'evidence clock') reduces immediate legibility but is internally consistent.

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

Usage Guidelines2/5

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

No explicit when-to-use guidance. The description implies a trade-safety guard context but never states when an agent should call it versus funding_stress_now or market_workbench, nor does it list prerequisites. A sibling-differentiated routing hint is absent.

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.