Skip to main content
Glama

Search federal contract awards

search_awards
Read-onlyIdempotent

Find who won Government of Canada contracts, for how much, and when to identify incumbents, competitor wins, and comparable prices before re-competition.

Instructions

Search Government of Canada award notices published on CanadaBuys since August 2022: which supplier won a contract, standing offer or supply arrangement, from which buyer, when, and for how much. Use it to find the incumbent before a re-competition, what similar work has sold for, which contracts end soon, or what a competitor has won. Each notice shows its latest amendment. Returns short summaries; call get_award for full details. With no arguments it lists the most recent awards. The first call downloads about 110 MB and can take a minute.

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_awards"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoOutput language.en
sortNoDefaults to relevance when a query is given, otherwise newest (by award date).
buyerNoWords from the contracting or end-user organization name, in either language. Public Services and Procurement Canada buys on behalf of other departments, which then appear as end users.
limitNoResults per page (1-50).
matchNoWhether a notice must contain all query terms or any of them. An explicit OR in the query always applies.all
queryNoKeywords searched in titles, descriptions, commodity names, supplier and buyer names, and solicitation and contract numbers. Words match in English and French, ignoring case and accents. Use "double quotes" for an exact phrase, a trailing * for a prefix (engineer*), and uppercase OR between alternatives.
offsetNoResults to skip, for paging.
regionNoText contained in a region of delivery, e.g. "Ontario" or "National Capital Region".
unspscNoUNSPSC commodity code or prefix. A segment or family code such as 43000000 or 4323 also matches every code beneath it.
categoryNoProcurement categories; an award matching any listed category is returned.
supplierNoWords from the winning supplier's legal name, e.g. "Deloitte".
max_valueNoOnly awards with a stated value of at most this amount.
min_valueNoOnly awards worth at least this amount, in the contract currency (almost always CAD). Above zero, this drops awards with no stated value.
competitiveNotrue for competitively awarded contracts only; false for non-competitive awards and advance contract award notices only. Awards with no stated method match neither.
awarded_afterNoOnly contracts awarded on or after this date (YYYY-MM-DD).
awarded_beforeNoOnly contracts awarded on or before this date (YYYY-MM-DD).
include_cancelledNoAlso return cancelled award notices.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.1

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already establish readOnly, idempotent and openWorld, so the safety profile is covered. The description adds genuinely useful operational context the annotations cannot: an initial ~110 MB download that can take a minute, and that only the latest amendment of each notice is shown. It does not mention pagination limits or result caps, but the latency and data-freshness disclosures are the high-value items here.

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?

Four sentences, front-loaded with scope, then scenarios, then return shape and the get_award pointer, then the cold-start warning. Every sentence carries information an agent needs before invoking, and nothing is padded.

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 17-parameter search tool with no output schema, the definition covers purpose, query intent, default behavior, result granularity (short summaries) and the expensive first-call caveat. An agent can select and invoke it correctly without further inference.

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 description coverage is 100%, so all 17 parameters are already documented in detail, including query syntax and UNSPSC prefix matching. The description contributes only the no-argument default behavior, which overlaps with the schema's own sort default note. Baseline 3 is appropriate.

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 Government of Canada award notices on CanadaBuys since August 2022) and enumerates exactly what a record answers: supplier, buyer, date, value, plus contract/standing offer/supply arrangement types. It also distinguishes itself from get_award, which returns full details, so the agent knows which of the two to reach for.

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?

Gives concrete when-to-use scenarios (find the incumbent before a re-competition, comparable sale prices, contracts ending soon, competitor wins) plus the fallback behavior when no arguments are supplied. It lacks an explicit contrast with the search_tenders and search_standing_offers siblings, so the agent must infer that this tool covers awarded/closed procurement rather than open opportunities.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.