Skip to main content
Glama

Search deals

search_deals
Read-onlyIdempotent

Find deals in the Corridome register by company name (one part of a name, or a list of parts searched together), by a firm and its role and side (or by several firms at once, firm_ids), by the kind and state of firm, the deal type, the company's sector (one or a list), the disclosed value and the year. Returns how many deals match (total) and each deal's company, date, type, value, and its parties with their roles (the buyer, the seller and each side's advisers), newest first: read who bought, sold and advised from these parties, without opening each deal. Every word and sector a question names goes in one search. For the buyers themselves, counted and ranked, use find_buyers; for counts by year, type or sector, count_records.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_deals"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoWhich page of results, from 1.
roleNoThe matching firm's role on the deal. sell-side adviser advised the seller; buy-side adviser advised the buyer.
sideNoWhich side the matching firm was on: the buyer and its advisers, or the seller and its advisers.
limitNoHow many results to return, 1 to 50.
stateNoThe US state of the matching firm's main office, as a two-letter code. It is the firm's state, not the company's.
sectorNoThe target company's sector, or a list of sectors searched together in this one call.
companyNoPart of the company's name, as filings write it; or a list of up to 20 parts searched together in this one call, a deal matching when its company's name holds any of them: ["utility", "substation", "excavat"]. Give every word the question names in one search, never one search a word.
firm_idNoOnly deals this firm worked on: its id from search_firms, or its corridome.com address.
year_toNoLast year, inclusive.
firm_idsNoSeveral firms at once, up to 25: deals any of them worked on, newest first, each saying which of them it matched. Use this, not one search a firm, whenever the question is about a set of firms (which of these buyers did a deal since 2025). Each firm's id from search_firms or get_firm, or its corridome.com address.
deal_typeNoThe kind of deal.
firm_kindNoThe kind of firm that matches. adviser: investment advisers registered with the SEC, and exempt reporting advisers. broker-dealer: registered broker-dealers. other: firms known from their own websites and filings.
year_fromNoFirst year, inclusive.
max_value_musdNoHighest disclosed value, in millions of US dollars. Only deals with a disclosed value match.
min_value_musdNoLowest disclosed value, in millions of US dollars. Only deals with a disclosed value match.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changed
    • addedInput schema / properties / company / anyOf
      Added value: +[
      +  {
      +    "maxLength": 80,
      +    "minLength": 2,
      +    "type": "string"
      +  },
      +  {
      +    "items": {
      +      "maxLength": 80,
      +      "minLength": 2,
      +      "type": "string"
      +    },
      +    "maxItems": 20,
      +    "minItems": 1,
      +    "type": "array"
      +  }
      +]
    • changedInput schema / properties / company / description
      Previous value: -"Part of the company's name, as filings write it."New value: +"Part of the company's name, as filings write it; or a list of up to 20 parts searched together in this one call, a deal matching when its company's name holds any of them: [\"utility\", \"substation\", \"excavat\"]. Give every word the question names in one search, never one search a word."
    • removedInput schema / properties / company / maxLength
      Removed value: -80
    • removedInput schema / properties / company / minLength
      Removed value: -2
    • removedInput schema / properties / company / type
      Removed value: -"string"
    • addedInput schema / properties / sector / anyOf
      Added value: +[
      +  {
      +    "enum": [
      +      "AI & Data",
      +      "Aerospace & Defense",
      +      "Agriculture",
      +      "Business Services",
      +      "Construction & Infrastructure",
      +      "Consumer & Retail",
      +      "Education",
      +      "Energy & Power",
      +      "Financial Services",
      +      "Food & Beverage",
      +      "Government & Nonprofit",
      +      "Healthcare Services",
      +      "Hospitality & Leisure",
      +      "Industrials & Manufacturing",
      +      "Insurance",
      +      "Life Sciences & Pharma",
      +      "Media & Entertainment",
      +      "Medical Devices",
      +      "Real Estate",
      +      "Software & IT",
      +      "Telecom",
      +      "Transportation & Logistics",
      +      "Other"
      +    ],
      +    "type": "string"
      +  },
      +  {
      +    "items": {
      +      "enum": [
      +        "AI & Data",
      +        "Aerospace & Defense",
      +        "Agriculture",
      +        "Business Services",
      +        "Construction & Infrastructure",
      +        "Consumer & Retail",
      +        "Education",
      +        "Energy & Power",
      +        "Financial Services",
      +        "Food & Beverage",
      +        "Government & Nonprofit",
      +        "Healthcare Services",
      +        "Hospitality & Leisure",
      +        "Industrials & Manufacturing",
      +        "Insurance",
      +        "Life Sciences & Pharma",
      +        "Media & Entertainment",
      +        "Medical Devices",
      +        "Real Estate",
      +        "Software & IT",
      +        "Telecom",
      +        "Transportation & Logistics",
      +        "Other"
      +      ],
      +      "type": "string"
      +    },
      +    "maxItems": 8,
      +    "minItems": 1,
      +    "type": "array"
      +  }
      +]
    • changedInput schema / properties / sector / description
      Previous value: -"The target company's sector."New value: +"The target company's sector, or a list of sectors searched together in this one call."
    • removedInput schema / properties / sector / enum
      Removed value: -[
      -  "AI & Data",
      -  "Aerospace & Defense",
      -  "Agriculture",
      -  "Business Services",
      -  "Construction & Infrastructure",
      -  "Consumer & Retail",
      -  "Education",
      -  "Energy & Power",
      -  "Financial Services",
      -  "Food & Beverage",
      -  "Government & Nonprofit",
      -  "Healthcare Services",
      -  "Hospitality & Leisure",
      -  "Industrials & Manufacturing",
      -  "Insurance",
      -  "Life Sciences & Pharma",
      -  "Media & Entertainment",
      -  "Medical Devices",
      -  "Real Estate",
      -  "Software & IT",
      -  "Telecom",
      -  "Transportation & Logistics",
      -  "Other"
      -]
    • removedInput schema / properties / sector / type
      Removed value: -"string"
  2. Changed1 schema field changed
    • addedInput schema / properties / firm_ids
      Added value: +{
      +  "description": "Several firms at once, up to 25: deals any of them worked on, newest first, each saying which of them it matched. Use this, not one search a firm, whenever the question is about a set of firms (which of these buyers did a deal since 2025). Each firm's id from search_firms or get_firm, or its corridome.com address.",
      +  "items": {
      +    "maxLength": 300,
      +    "minLength": 2,
      +    "type": "string"
      +  },
      +  "maxItems": 25,
      +  "minItems": 1,
      +  "type": "array"
      +}
  3. 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 closed-world, so the safety profile needs no restating. The description adds real behavior beyond that: results are ordered newest first, the response carries a total match count, and party roles (buyer, seller, each side's advisers) are inlined so the agent can answer ownership/advice questions "without opening each deal" — avoiding an N+1 pattern of get_deal calls. Pagination behavior is left to the schema rather than described here.

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 purpose and the two sibling hand-offs are front-loaded and every sentence carries information. The opening enumeration sentence is long and comma-heavy, and it partly restates filter names already documented in the schema, but nothing is genuinely redundant enough to cut.

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?

For a 15-parameter, zero-required search tool with no output schema, the description is complete: it covers what filters exist, how they combine, what the response contains (total plus per-deal parties and roles), and ordering. Annotations cover the safety/hint profile and the schema covers paging, so no critical gap remains for correct invocation.

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, but the description adds query semantics the schema encodes only piecemeal: filters across dimensions combine in one call, while lists (company parts, sectors, firm_ids) are OR'd within a dimension, and every named word/sector belongs in a single search. That combined-filter model is genuinely beyond the per-field schema text.

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?

Names a specific verb and resource ("Find deals in the Corridome register") and enumerates the exact filter dimensions: company name, firm + role/side, firm kind/state, deal type, sector, value and year. It also states what is returned (total plus each deal's company, date, type, value and parties with roles), so an agent can distinguish it from find_buyers, count_records and get_deal 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 Guidelines5/5

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

Explicitly routes away from this tool in two concrete cases: "For the buyers themselves, counted and ranked, use find_buyers; for counts by year, type or sector, count_records." It also gives a positive usage rule for batching ("Give every word the question names in one search, never one search a word" and "Use this, not one search a firm, whenever the question is about a set of firms"), which is exactly the selection guidance an agent needs.

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