Skip to main content
Glama

Last night

last_night
Read-onlyIdempotent

What changed in StockMap's calls last night: how many stocks' calls changed band on the market map and the biggest of them, the calls graded last night (made 14 days earlier) with one line on why each was right or wrong, and when the next run starts. Each answer carries the not-advice line and the run date.

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": "last_night"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Output Schema

NameRequiredDescriptionDefault
runYesThe run the night is from: the day it ran and the close it called from
gradedNoThe calls graded last night
gradesYes
changesYesThe biggest of them by market cap
not_adviceNoThe model's track-recorded read, not financial advice.
record_urlNohttps://stockmap.io/track-record
calls_issuedNoCalls the run made
more_changesYesThe changes not listed; all of them are on /what-changed
next_run_utcNoWhen the next run starts
run_in_flightYesTrue: tonight's run has not landed yet, so this is the previous night (B2's name for run.not_landed)
changed_on_mapNoStocks whose call changed band on the map
all_changes_urlNohttps://stockmap.io/what-changed

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / $defs / Graded / properties / base_rate_pct / description
      Previous value: -"How often a blind call on the same dates was right, over all stocks (a market number, not a score of these calls)"New value: +"How often a random call on the same dates was right, over all stocks (a market number, not a score of these calls)"
  2. Changed4 schema fields changed
    • removedOutput schema / $defs / Grade / properties / actual_delta
      Removed value: -{
      -  "description": "How far the stock moved against the index over the window, in %",
      -  "title": "Actual Delta",
      -  "type": "number"
      -}
    • changedOutput schema / $defs / Grade / required
      Previous value: -[
      -  "symbol",
      -  "called",
      -  "actual_delta",
      -  "verdict",
      -  "why"
      -]New value: +[
      +  "symbol",
      +  "called",
      +  "verdict",
      +  "why"
      +]
    • addedOutput schema / $defs / Graded / properties / base_rate_pct
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "number"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "How often a blind call on the same dates was right, over all stocks (a market number, not a score of these calls)",
      +  "title": "Base Rate Pct"
      +}
    • addedOutput schema / $defs / Graded / properties / chance
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "The base rate as one sentence, or None when there is none",
      +  "title": "Chance"
      +}
  3. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already cover read-only, idempotent, closed-world and non-destructive, so safety is not the description's job here. The description adds real behavioral detail the annotations do not: that graded calls were made 14 days earlier, that every answer includes the not-advice line and the run date, and that the next run time is part of the payload.

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?

One dense sentence, but it is front-loaded with the core question ('What changed') and each of the three clauses maps to a distinct part of the answer. It could be split for readability, but no clause is filler.

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?

A no-parameter, read-only snapshot tool with an output schema, so return shape need not be spelled out. The description still covers the three content blocks and the fixed disclaimers, leaving only minor ambiguity about scope (whether coverage is all markets or a single map).

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?

There are zero parameters, so there is no parameter meaning to convey; the 100% schema coverage confirms nothing is hidden. Baseline for a no-parameter tool 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?

The description states specifically what the tool reports: band changes on the market map, the calls graded last night (with the 14-day lag named), and the next run start. That is concrete enough to distinguish it from the map-viewing siblings such as market_map, though it never names an alternative directly.

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

Usage Guidelines3/5

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

The 'last night' framing implies a daily recap use case, but there is no explicit when-to-use or when-not guidance and no sibling is pointed to as the alternative for adjacent needs. Usage is inferable rather than stated.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources