Skip to main content
Glama

Capital Signal: ASX announcements

Search filings

search_filings
Read-onlyIdempotent

Full-text search across ASX announcement filings, returning snippets of what filings say - commentary, explanations and wording - rather than structured figures. Suited to questions about specific disclosure language where no structured field covers it. Each call costs 1 credit. Queries of 2-5 keywords work best; a longer query that matches nothing is retried once with its key terms, and the response says so. Results carry doc_keys, which identify filings that filing_text reads in full. If a response has truncated=true the match pool was larger than the page: narrower parameters are symbol, match='phrase' for exact disclosure language, and the event, types and date bounds. Structured numbers for one company are in company_events.

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": {
      "query": "<query>"
    },
    "name": "search_filings"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoOptional latest date YYYY-MM-DD.
tagNoOptional company tag/sector filter, e.g. 'Copper'.
fromNoOptional earliest date YYYY-MM-DD.
tierNoOptional: T1 (market-moving only), T2, or T3.
eventNoOptional known announcement kind (suspension, takeover, guidance_revision, capital_raise, buyback, distress, trading_update, consolidation) — event matching bypasses text ranking entirely.
limitNoMax hits (default 10, max 25).
matchNoOptional: 'phrase' for exact adjacent-word matching.
queryYesSearch terms, e.g. 'share purchase plan' or 'BHM'.
typesNoOptional comma-separated ASX announcement types, e.g. 'Appendix 3Y,Appendix 4C'.
symbolNoOptional ticker filter, e.g. 'BHM'.
priceSensitiveNoOptional: only price-sensitive filings, or only not.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds context annotations cannot: a 1-credit per-call cost, an automatic single retry for long zero-hit queries with the response disclosing that, and the meaning of truncated=true and doc_keys. The only gap is no statement on result ordering or pagination mechanics beyond limit.

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-loaded with purpose and payoff, and nearly every sentence carries distinct information (cost, retry, doc_keys, truncation remedy). Some sentences are long and clause-stacked, which slightly hurts scannability.

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?

With no output schema, the description carries the burden and does so: it describes the snippet-based return, the doc_keys handoff to filing_text, the truncated indicator, and the retry notice. An agent has everything needed to call it, interpret results, and decide a follow-up.

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 100%, so the baseline is 3; the description still adds operational meaning by naming exactly which parameters narrow a too-large match pool (symbol, match='phrase', event, types, date bounds) and pairing match='phrase' with exact disclosure-language questions. It does not restate formats, but the extra routing value is real.

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 ('Full-text search across ASX announcement filings') and immediately defines the return shape ('snippets of what filings say ... rather than structured figures'). It also distinguishes itself from company_events for structured numbers and from filing_text for full documents, so an agent can route without opening schemas.

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

Usage Guidelines5/5

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

Explicit about when to use it ('questions about specific disclosure language where no structured field covers it') and names the alternatives for other cases (company_events for numbers, filing_text for full documents). It also gives tactical guidance on query length and what to do when truncated=true.

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