mcp-server

Rate change feed (observations)

get_rate_changes

Read-onlyIdempotent

The immutable rate-change log: every material yield move with full provenance (previous rate, raw value, multiplier, collection method, confidence, base/bonus split). Time-ascending pages via cursor. Unfiltered windows are capped at 31 days — filter by provider or symbol to walk deep history. Use for "what changed since X?" and audit trails.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "since": "<since>"
    },
    "name": "get_rate_changes"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Page size, default 100
`since`	Yes	ISO date/datetime lower bound (required), e.g. "2026-08-01"
`until`	No	ISO upper bound, default now
`cursor`	No	Opaque cursor from a previous page
`symbol`	No	Filter to one symbol, e.g. "USDC"
`category`	No
`provider`	No	Filter to one provider (enables deep ranges)

Output Schema

Name	Required	Description	Default
`data`	Yes
`pagination`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 2, 2026
- removedOutput schema / properties / data / items / properties / confidence / anyOf
```
Removed value: -[
-  {
-    "type": "integer"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / data / items / properties / confidence / type
```
Added value: +[
+  "integer",
+  "null"
+]
```
AddedAug 17, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare read-only/idempotent/non-destructive, and the description still adds real behavioral context: the log is immutable, ordering is time-ascending, paging is cursor-based, and unfiltered queries are capped at 31 days. That cap is the kind of operational trait an agent cannot infer from the schema and would otherwise trip over.

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?

Three tight sentences: identity, paging/ordering, then constraint plus use cases — front-loaded and waste-free. The parenthetical provenance list is dense but earns its place by signaling response shape.

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 7-parameter filtered feed with an output schema, the description covers purpose, ordering, paging, the 31-day cap, and the filter workaround. Nothing an agent needs to call this correctly is missing, and return values are legitimately left to the output schema.

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?

Schema coverage is 86%, so the baseline is 3; the description adds meaning on top by explaining the since/window semantics and, critically, that provider or symbol filtering unlocks ranges beyond the 31-day unfiltered cap. It does not clarify limit, cursor, or category behavior beyond what the schema states.

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?

Opens with a precise verb+resource framing ('immutable rate-change log: every material yield move') and enumerates the provenance payload, which clearly separates it from rate-snapshot siblings like get_rate_history or get_rates. An agent can tell this is a change feed rather than a current-state lookup without opening the schema.

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 concrete invocation contexts ('what changed since X?', audit trails) and a hard operational constraint: unfiltered windows are capped at 31 days, so filter by provider or symbol for deep history. It does not name a specific sibling alternative, which keeps it below a 5.

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

All mcp-server 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?