Skip to main content
Glama

Capital Signal: ASX announcements

Lock call

lock_call

Creates a permanent, public record in the Capital Signal calls ledger: a call or prediction that anyone can read and that cannot be edited or deleted (a correction is a new call with supersedes = the old call_id). The server stamps the time, so a call records only what was said before then. A call is relative: direction 'long' means the tickers (equal-weight) beat the benchmark over horizonDays trading days, 'short' means they lag it; it is scored automatically once the horizon passes (close before the first session it could act on to the close on day horizonDays). thesis holds the reasoning, evidenceDocKeys the filings behind it, and baseRate the base rate behind it (sample, N and hit rate) where one backs it. Returns call_id, created_at, sha256 and the canonical JSON that was hashed; the hash is published at /calls.txt. Suited to explicit user requests to lock, record, timestamp or publish a call. Free.

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": {
      "tickers": "<tickers>",
      "direction": "<direction>",
      "horizonDays": "<horizonDays>",
      "thesis": "<thesis>"
    },
    "name": "lock_call"
  }
}

Input Schema

NameRequiredDescriptionDefault
labelNoOptional author label, e.g. 'newsletter' or an agent run id; the author is the caller's public pseudonym plus this label.
rulesNoOptional machine-checkable exit rules, hashed with the call and checked every trading day. Each has a unique id and a type: price_above/price_below {level, action: take_profit|exit|review}; date {deadline: YYYY-MM-DD, event}; metric {metric, op: <,<=,>,>=,=, threshold, period}; event {match, action}. The prose exit rule stays in the thesis.
thesisYesWhy, in the user's words where possible (10-10,000 characters).
tickersYes1-20 ASX codes, e.g. ['SVM']; several = an equal-weight basket.
baseRateNoThe base rate used: its parameters plus N and hit rate / median excess, e.g. {dimension:'director_joins', priorTercile:'top', horizon:250, n:32, beatBenchmarkPct:43.8}.
benchmarkNoCS200EW (default, equal-weight ASX 200 proxy) or 'EW:<industry group>'.
directionYeslong = beats the benchmark; short = lags it.
supersedesNocall_id of the author's earlier call this one corrects.
horizonDaysYesTrading days to the verdict, 1-750 (60 ~ 3 months, 120 ~ 6, 250 ~ a year).
evidenceDocKeysNodoc_keys of the filings the call rests on.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / rules
      Added value: +{
      +  "description": "Optional machine-checkable exit rules, hashed with the call and checked every trading day. Each has a unique id and a type: price_above/price_below {level, action: take_profit|exit|review}; date {deadline: YYYY-MM-DD, event}; metric {metric, op: <,<=,>,>=,=, threshold, period}; event {match, action}. The prose exit rule stays in the thesis.",
      +  "items": {
      +    "type": "object"
      +  },
      +  "type": "array"
      +}
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Goes well past the annotations by disclosing permanence and immutability, the correction path via supersedes, server-side timestamping, the automatic scoring rule and settlement window, and the returned fields with the published hash. These are exactly the behavioral traits an agent needs before committing an irreversible write.

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?

Front-loads the immutable-record purpose and the when-to-use rule early, so the key decision points come first. It is dense and slightly long, with one clause that echoes schema descriptions, but almost every sentence carries operational value.

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 10-parameter, non-idempotent mutation with nested rule objects and no output schema, the description covers mutability, settlement/scoring, supersession, and the return payload including the published hash. Nothing material is left for the agent to infer.

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 already 100%, so a baseline of 3 applies, but the description adds real meaning: 'long' means the tickers beat the benchmark over horizonDays and 'short' means they lag, plus what supersedes and the hash artifacts represent. The thesis/evidenceDocKeys/baseRate clause largely restates schema text, keeping it from a 5.

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?

States a specific verb and resource — 'Creates a permanent, public record in the Capital Signal calls ledger' — and immediately characterizes the artifact as an immutable call/prediction. It is clearly distinguishable from read-oriented siblings like calls or call_scorecard.

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?

Explicitly scopes usage to 'explicit user requests to lock, record, timestamp or publish a call', which tells the agent when to reach for it. It does not name a specific alternative or spell out when NOT to use it (e.g. versus merely browsing calls), so it falls short of a 5.

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