Skip to main content
Glama

Capital Signal: ASX announcements

Find peers

find_peers
Read-onlyIdempotent

Comparable ASX companies for one company: same GICS sub-industry (widening to industry, then industry group, only when fewer than 3 match; each row says matchedOn), market cap within 0.1-10x, ordered by size proximity, each flagged for a raise in the last 12 months, M&A involvement and cash runway. Suited to 'peers', 'comparables', 'competitors' and 'how does X stack up' questions, which need an enumerated size band. 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": {
      "symbol": "<symbol>"
    },
    "name": "find_peers"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax peers, 1-20 (default 8).
symbolYesASX ticker in UPPERCASE, e.g. 'THL'.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the safety burden is covered. The description still adds genuine value beyond them: the tiered widening rule with a threshold of 3, the 0.1-10x market-cap band, ordering by size proximity, a matchedOn column, and per-row flags for raises, M&A and cash runway, plus the 'Free' cost note. It omits fallback behavior when fewer than 3 matches exist at any tier and says nothing about response size or pagination 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 the core verb and resource, then the matching logic, then the use-case sentence; nothing is padding. It is quite densely packed into two long clauses, and the phrase 'which need an enumerated size band' is slightly opaque, so it is efficient but not maximally scannable.

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?

With no output schema, the description carries the return-shape burden and does so well by naming matchedOn and the three per-row flags. The remaining gap is edge-case behavior: what the tool does if fewer than 3 companies match even at the widest tier, and whether limit applies per tier or overall.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%: symbol is documented as an uppercase ASX ticker with an example and limit is documented as 1-20 defaulting to 8. The description adds no parameter-level detail (it never mentions limit or explains that it caps the peer list), so the baseline 3 is appropriate.

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 (comparable ASX companies for one company) plus the exact matching rule (same GICS sub-industry, widening to industry then industry group). This is clearly distinguishable from sibling screening/profile tools, so an agent can pick it 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 explicit trigger phrasings ('peers', 'comparables', 'competitors', 'how does X stack up') and a key condition (questions that need an enumerated size band), which is a real routing signal. It stops short of naming an alternative tool or stating when not to use it, so it is strong context rather than full when/when-not guidance.

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