Skip to main content
Glama

Worldbank Procurement

Wb Procurement Awards

wb_procurement_awards
Read-onlyIdempotent

Search World Bank contract awards, which contracts were awarded under World Bank-financed development projects (300k+ award notices across developing countries). Filter by full-text keyword and/or country to see recently awarded goods, civil works, and consulting contracts, each with project, bid reference, procurement method, award publication date, and a public notice URL (the notice detail page names the awarded supplier). Newest first. Keyless.

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": {
      "limit": 10,
      "query": "bridge construction",
      "country": "Ethiopia"
    },
    "name": "wb_procurement_awards"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoNumber of awards to return (1-50). Default 10.
queryNoFull-text keyword, e.g. "bridge construction", "audit services", "medical equipment". Optional.
offsetNoResult offset for pagination. Default 0.
countryNoCountry name (plain English), e.g. "Kenya", "Ethiopia", "Vietnam". Optional.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / examples
      Added value: +[
      +  {
      +    "country": "Ethiopia",
      +    "limit": 10,
      +    "query": "bridge construction"
      +  },
      +  {
      +    "limit": 25,
      +    "offset": 0,
      +    "query": "medical equipment"
      +  }
      +]
  2. First observed

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, open-world, non-destructive, so the safety profile needs no restating. The description does add genuine value beyond them: 'Keyless' (no auth required), 'Newest first' ordering, corpus size, and the important caveat that the awarded supplier is only named on the linked notice detail page rather than in the result. It stops short of return shape or page-size/truncation behavior, so it is solid but not rich.

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?

Three sentences, front-loaded with the verb and resource, then the filter behavior, then the return fields and ordering. Dense and largely waste-free, though the long parenthetical packing in corpus size, contract types, and six fields is heavy for one clause.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly takes on the burden of describing what comes back (project, bid reference, procurement method, award date, notice URL) and the ordering. What it omits matters for a paginated search tool: no indication of total result counts, whether more pages exist, or how the 1-50 limit interacts with offset beyond what the schema states.

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 100% and every parameter already carries its own description and default, so the baseline of 3 applies. The description reinforces the semantics of query and country by giving example values ('bridge construction', 'Ethiopia') and noting both filters can be combined, but adds no syntax, matching, or validation detail beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Search World Bank contract awards') plus concrete scope: 300k+ award notices, goods/civil works/consulting contracts, with the exact fields returned. It is clear what the tool does, but it never distinguishes itself from the clearly related siblings wb_procurement_search, wb_procurement_by_country, and wb_procurement_detail, which an agent could easily confuse with this one.

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?

The phrase 'Filter by full-text keyword and/or country' implies the use case (keyword and/or country lookup), so usage is inferable but never stated as guidance. There are no exclusions and no mention of when to prefer the sibling search, by-country, or detail tools, which is a real gap given how much the sibling names overlap.

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.