Skip to main content
Glama
tearsheet

tearsheet

by kewonit

compare_companies

Read-only

Compare 2 to 6 companies side by side on valuation, returns and growth, including annual revenue and net profit growth, three-year revenue CAGR, and minimum, median and maximum values for each figure.

Instructions

Compare 2 to 6 companies side by side on valuation, returns and growth.

    Growth is calculated here from annual figures, never from TTM or
    interim columns: revenue and net profit growth in the latest year,
    and three-year revenue CAGR. Growth is blank where it isn't defined,
    such as from a loss. Also gives the minimum, median and maximum of
    each figure. For a company's own peer list, see company_snapshot.
    

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": {
      "companies": "<companies>"
    },
    "name": "compare_companies"
  }
}

Input Schema

NameRequiredDescriptionDefault
companiesYes

Output Schema

NameRequiredDescriptionDefault
dataYes
as_ofNo
unitsNo
entityNo
sourcesNo
warningsNo
next_cursorNo
retrieved_atNo
verificationNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=true; the description goes well beyond that by disclosing the growth methodology (annual figures, never TTM or interim columns), what growth is computed (latest-year revenue and net profit growth, three-year revenue CAGR), and that growth is blank where undefined such as from a loss. It also notes the min/median/max aggregation. Auth requirements and response shape are left implicit, but the calc semantics are unusually well disclosed.

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?

The core capability is front-loaded in one sentence, with the calculation caveats following. The growth-methodology sentences earn their space because they prevent a real misuse (expecting TTM growth), though the phrasing is slightly redundant between "never from TTM or interim columns" and the blank-value note.

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?

An output schema exists, so return values needn't be explained, and the description still adds useful framing about the aggregation (min/median/max) and blank handling. The main gap is the identifier format for the companies array, which is critical to calling it correctly.

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 coverage is 0%, so the description must carry the load. It confirms the 2-to-6 cardinality matching the minItems/maxItems constraints, but never says what the string entries should be — ticker, company name, or ID — nor whether they must be homogeneous. Partial compensation for a single undocumented parameter.

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 (compare), a specific resource (companies), an explicit cardinality bound (2 to 6), and the dimensions covered (valuation, returns, growth). An agent can distinguish this from company_snapshot or get_financials without opening a 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?

Explicitly routes the agent elsewhere for a company's own peer list ("see company_snapshot"), which is genuine when-to-use guidance. It does not cover when to prefer get_financials or screen_stocks for single-company or screening cases, so the routing is clear but not exhaustive.

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