Skip to main content
Glama

Annalist Financial Statements

Run a buyout model

run_buyout
Read-onlyIdempotent

Run the buyout model 1.0 of Annalist Deal Lab on a company's published figures, at its starting values or with the caller's assumptions under the keys of the address of the page (entry, exit_mult, years, debt, growth, margin, tax, base and the others that the starting values list). Returns the returns, sources and uses, the debt schedule, the covenants and the checks of the model, optionally the 3 solvers, every input with its source document ids, and the address of the same deal on the site. Shares and rates are fractions (0.2 for 20%) and multiples are times EBITDA. The result is arithmetic on published figures and the caller's assumptions: it values no company, recommends no transaction and forecasts nothing.

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": {
      "company": "<company>"
    },
    "name": "run_buyout"
  }
}

Input Schema

NameRequiredDescriptionDefault
companyYescompany id from search_companies, for example apple
solversNoalso return the highest entry multiple for the target return, the growth it needs and the debt capacity
assumptionsNoassumptions to change, for example {"entry": 8, "debt": 4}; leave out for the starting values

Output Schema

NameRequiredDescriptionDefault
okYes
baseNo
nameNo
modelYes
inputsNo
addressYes
companyYes
returnsNo
solversNo
citationYes
computedNo
currencyNo
snapshotYes
projectionNo
assumptionsYes
debt_scheduleNo
failed_checksNo
return_bridgeNo
sources_and_usesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "address": {
      +      "type": "string"
      +    },
      +    "assumptions": {
      +      "type": "object"
      +    },
      +    "base": {},
      +    "citation": {
      +      "type": "string"
      +    },
      +    "company": {
      +      "type": "string"
      +    },
      +    "computed": {
      +      "type": "string"
      +    },
      +    "currency": {},
      +    "debt_schedule": {
      +      "type": "object"
      +    },
      +    "failed_checks": {},
      +    "inputs": {
      +      "type": [
      +        "object",
      +        "null"
      +      ]
      +    },
      +    "model": {
      +      "type": "object"
      +    },
      +    "name": {
      +      "type": "string"
      +    },
      +    "ok": {
      +      "type": "boolean"
      +    },
      +    "projection": {
      +      "type": "object"
      +    },
      +    "return_bridge": {
      +      "type": [
      +        "object",
      +        "null"
      +      ]
      +    },
      +    "returns": {
      +      "type": [
      +        "object",
      +        "null"
      +      ]
      +    },
      +    "snapshot": {
      +      "type": "string"
      +    },
      +    "solvers": {
      +      "type": "object"
      +    },
      +    "sources_and_uses": {
      +      "type": "object"
      +    }
      +  },
      +  "required": [
      +    "company",
      +    "snapshot",
      +    "model",
      +    "assumptions",
      +    "ok",
      +    "address",
      +    "citation"
      +  ],
      +  "type": "object"
      +}
  2. Added

TDQS

A4/5.0
Behavior4/5

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 bar is low. The description still adds real value beyond them: it fixes unit conventions (fractions for shares and rates, multiples as times EBITDA) and explicitly frames the output as arithmetic on published figures that 'recommends no transaction and forecasts nothing' — an important expectation-setting trait. It stops short of any runtime characteristics such as latency or validation failures.

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?

Purpose and scope are front-loaded well, but the middle sentence is a dense run-on enumerating outputs and input keys, including a vague trailing clause. It is longer than needed, and part of the return-value enumeration duplicates what the output schema already supplies.

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 annotations and an output schema present, the description covers the essentials: input modes, units, and result scope. It spends effort re-listing return fields the output schema already documents, while leaving unstated what happens on invalid assumption keys or missing figures.

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 baseline is 3, but the description goes further by naming the assumption keys (entry, exit_mult, years, debt, growth, margin, tax, base) that the schema leaves as an untyped number map, and by giving the unit convention for them. The phrase 'and the others that the starting values list' leaves the enumeration incomplete, 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 ('Run the buyout model 1.0 ... on a company's published figures') and implicitly separates itself from the fetch/search/compare siblings by being the only computation tool. An agent can identify what it does and what it returns 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 Guidelines3/5

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

Explains the two input modes ('at its starting values or with the caller's assumptions') and the optional solvers switch, which is useful context. But it never states when to reach for this versus sibling tools or what prerequisites exist beyond the company id, so usage is implied rather than directed.

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