Skip to main content
Glama

Idb Search Awards

idb_search_awards
Read-onlyIdempotent

Search Inter-American Development Bank (IDB) contract award data, which firms and individual consultants were awarded contracts under IDB-financed projects, with contract amount, sector, borrower country, and dates. ~159,000 awards. Filter by country, awarded firm name, sector, and contract year. Note: many individual-consultant contracts record the firm as "Not Available" by design (the consultant is not a named firm). Keyless, queried live against the same data as IDB's 70MB awards CSV, no download needed.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "firm": "Deloitte",
      "limit": 5
    },
    "name": "idb_search_awards"
  }
}

Input Schema

NameRequiredDescriptionDefault
firmNoAwarded firm name (partial/case-insensitive), e.g. "Deloitte", "Odebrecht".
yearNoContract signature year, e.g. 2025.
limitNoMax awards to return (1-50). Default 15.
sectorNoSector keyword, e.g. "Rural Electrification", "Health Services", "Water Supply".
countryNoBorrowing country, e.g. "Colombia", "Bolivia", "Ecuador". Partial/case-insensitive match.
keywordNoKeyword against the project name.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Goes meaningfully beyond the annotations (which already establish read-only, idempotent, open-world) by disclosing that the tool is keyless, queries live, and mirrors IDB's 70MB awards CSV — telling the agent there is no stale snapshot or download step. It also discloses a real data quirk: many individual-consultant contracts record the firm as 'Not Available' by design, which prevents the agent from misreading empty firm filters as missing data. It does not describe pagination beyond the limit param or response ordering.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences, front-loaded with the verb and resource, then scale, then filters, then the operational caveat. The 70MB CSV-equivalence sentence and the 'Not Available' note both carry information an agent would otherwise have to discover by trial.

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?

No output schema, but the description names the returned fields (contract amount, sector, borrower country, dates), the dataset scope (~159,000 awards), and the key data caveat, so an agent knows enough to call it and interpret results. Six optional parameters with 100% schema coverage leave no documentation gap.

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 real meaning for the 'firm' parameter by explaining that individual consultants are recorded as 'Not Available' by design, which changes how an agent should interpret a firm filter returning nothing. The enumerated filter list also mirrors the schema's country/firm/sector/year dimensions, confirming they compose as an AND-style filter set.

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 ('Search IDB contract award data'), names the entities involved (firms and individual consultants awarded contracts under IDB-financed projects), lists the returned fields, and gives dataset scale (~159,000 awards). An agent can distinguish this from idb_search_notices (tender notices) purely from the description.

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 enumerates the available filters (country, awarded firm name, sector, contract year) which signals the intended query patterns, and the opening clause frames the use case as 'which firms were awarded contracts.' It stops short of naming alternatives such as idb_search_notices or idb_get_notice for tenders or per-award detail, so there is no explicit 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.