Skip to main content
Glama

A company's public aid (BDNS)

company_grants
Read-onlyIdempotent

List the public aid awards that BDNS, Spain's national database of subsidies and other public aid, records for a company's tax ID, newest first.

Use it for a known company (a slug from search_companies).

Returns JSON {company_slug, nif, link, shown_from, data_as_of, attribution, totals {by_instrument, by_year}, count, next_offset, truncated, items [{concession_id, granted_on, instrument, amount_eur, aid_equivalent_eur, call {title, level, administration, body}}], note}. Only instrument subsidy is a grant: a loan's amount_eur is the principal lent and a guarantee's the amount guaranteed, so never call them grants. Totals are per instrument; do not add nominal amounts across instruments. Awards before shown_from are no longer shown by BDNS. Quote attribution and data_as_of with the data. An empty list means none is linked in our data, not that none was received.

Read-only. Needs the basic plan or higher: send your API key in the X-API-Key header (https://bormeapi.com/account).

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": "company_grants"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoAwards per page, integer 1-200, e.g. 20 (default 50).
offsetNoAwards to skip, integer 0-10000 (default 0); pass the previous page's next_offset, e.g. 50.
companyYesCompany slug, as returned by search_companies or company_history, e.g. vaz-metales-sl.
date_toNoOptional latest award date, YYYY-MM-DD, e.g. 2025-12-31.
date_fromNoOptional earliest award date, YYYY-MM-DD, e.g. 2024-01-01.
instrumentNoOptional list of aid instruments, each one of subsidy, loan, guarantee, tax_advantage, risk_finance, other, e.g. ["subsidy"]; omit for all.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Goes well past the annotations: authentication requirement ('send your API key in the X-API-Key header'), plan gating (basic or higher), truncation behavior via shown_from, the meaning of an empty result ('not that none was received'), and the attribution/data_as_of quoting obligation. The semantic warning about instrument types is the kind of domain caveat an agent could not infer from annotations.

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-loads purpose, then return shape, then caveats, then auth — a sensible order. The inline JSON type listing is dense but justified given there is no output schema; a few clauses (e.g. the loan/guarantee aside) could be tightened without losing meaning.

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?

With no output schema, the description carries the full burden of describing the response and it does so in detail, including pagination fields (next_offset, truncated) and totals structure. Combined with auth, plan tier, and data-interpretation caveats, an agent has everything needed to call and report results correctly.

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; the description earns above that by explaining that only the 'subsidy' instrument is a grant and that loan/guarantee amounts are principal/guaranteed amounts, which materially changes how the instrument filter and amount_eur should be read. It also explains that totals must not be summed across instruments and that records before shown_from are no longer surfaced by BDNS.

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 ('List the public aid awards that BDNS ... records for a company'), names the source database, the ordering ('newest first'), and the key input ('a slug from search_companies'). This is unmistakably distinct from sibling tools like company_contracts or company_snapshot without needing to name them.

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?

'Use it for a known company (a slug from search_companies)' gives a clear precondition and routes the agent to the sibling that produces the required identifier. It does not state exclusions or what to use instead if the company is unknown, which keeps it short of a 5.

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.