Skip to main content
Glama

Capital Signal: ASX announcements

Person profile

person_profile
Read-onlyIdempotent

One person - director, chair, CEO, CFO or company secretary - resolved across every ASX board they have sat on since 2018. Name variants ('Geoff Wilson', 'Mr G J Wilson') are joined only on evidence: a shared family trust or super fund in their 3Y notices, or a bio naming the other company (mergeStrength strong); a rare full name alone gives mergeStrength medium. Returns every tenure (role, from/to, fromCensored when first seen after 2018, outcome: current, resigned, retired, takeover with premium, administration, delisted, unrecorded) with its track record - share-price return vs CS200EW (annualised), capital raised, raises and deep-discount (20%+) raises, dilution, guidance given vs beat/in range/missed, the person's own on-market buys and sales - plus a summary, the holding entities that identify them, matchEvidence, possibleSameAs (same name, no evidence: not counted, may be someone else) and otherMatches when several people share the name (pass a personId to pick one). Every tenure carries docKeys. Caveats: records over-weight companies still listed (survivorship) and returns exclude dividends. Suited to 'who is X' and track-record questions about a person. 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": {
      "name": "<name>"
    },
    "name": "person_profile"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesThe person's name as filed or commonly used, e.g. 'Geoff Wilson', or a personId from another call.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only establish that this is a safe, idempotent read; the description goes well beyond that by disclosing the merge policy (strong vs medium mergeStrength and the evidence that produces each), the full outcome vocabulary for tenures, and the identity artifacts returned (holding entities, matchEvidence, possibleSameAs, otherMatches, docKeys). It also volunteers two real caveats — survivorship bias from over-weighting still-listed companies and returns excluding dividends — which materially affect how an agent should present results.

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?

The core purpose is front-loaded in the opening clause, but the body is a long run-on sentence that packs a dozen enumerated metrics plus caveats into one breath, making it hard to scan. Nearly every clause carries information, yet the density and jargon (3Y notices, CS200EW, deep-discount raises) cost readability.

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?

There is no output schema, so the description carries the full burden of explaining return values, and it does so thoroughly: per-tenure metrics, a summary, identity entities, match evidence, and disambiguation fields. Combined with the stated caveats and the free-access note, an agent has everything needed to call it and to caveat its answer appropriately.

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% for the single parameter and the schema already notes that a personId may be supplied instead of a name. The description adds genuine meaning on top by explaining that name variants ('Geoff Wilson' vs 'Mr G J Wilson') are only joined on evidence and that ambiguous names produce possibleSameAs/otherMatches rather than being silently merged, which tells the agent how matching actually behaves.

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?

The definition names a specific resource (one person) and its scope precisely: every ASX board seat since 2018, with name-variant resolution. It is clearly distinguishable from company-oriented siblings because the unit of analysis is a person and their tenures, and it even enumerates the roles covered (director, chair, CEO, CFO, company secretary).

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?

It states the intended questions explicitly ("who is X" and track-record questions about a person) and explains how to disambiguate when several people share a name by passing a personId. It does not, however, name an alternative sibling tool or say when a company-level lookup would be the better choice, so the routing guidance is implicit rather than explicit.

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