Tendy - Israeli public tenders

Search tenders

search_tenders

Read-onlyIdempotent

Search Israeli public tenders in Tendy's catalog by free text and filters. Tender data is Hebrew; query matches best in Hebrew, in the user's own words. By default only open procurement tenders are returned (published, submission deadline still ahead), the same default as the Tendy website search; status and record_kind widen it. When the topic is one of the list_categories categories, category finds it more precisely than query. For an overview of a category, a publishing body, a region, or government or municipal tenders, browse_collection answers in one call. To find a tender by its number or by the body that published it, use tender_number or publisher. Returns up to 10 tenders per page with deadline, category, city, region and a link to the tender page. Each row has knowledge.completeness: partial or listing_only means Tendy could not read all of that tender's documents; the tender is still a valid result and is not ranked lower. filters_applied.sort_applied is the order actually used.

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_tenders"
  }
}

Input Schema

Name	Required	Description	Default
`page`	No	Result page, from 1.
`sort`	No	relevance or deadline (soonest first). Free-text search orders by relevance; filters_applied.sort_applied is the order used.
`query`	No	Hebrew free text, as the user wrote it.
`region`	No	One of the listed Israeli districts; ארצי means nationwide.
`status`	No	open: deadline still ahead (default). active: published, including tenders whose deadline passed but are not yet archived. archived: closed and archived. all: everything public, including tenders with no known deadline.	open
`category`	No	Category slug or Hebrew name from list_categories. When the topic is a category, this matches it more precisely than free text; a parent category includes its subcategories.
`closes_by`	No	Only tenders whose submission deadline is on or before the end of this day, Israel time (YYYY-MM-DD), for 'closing this week' questions. Combine with sort=deadline. Tenders with no known deadline are left out.
`publisher`	No	The publishing body's Hebrew name, as written on the tender. An unknown name returns close matches.
`record_kind`	No	procurement_tender (default): tenders only. all: also award notices, cancellations and other publication types.	procurement_tender
`supplier_size`	No	Tender size band from Tendy's supplier-fit signal. Tenders Tendy could not size are still included; their supplier_fit is null.
`tender_number`	No	The tender number as the publisher writes it, for example 12/2026. Slash, dash and space are treated alike.

Output Schema

Name	Required	Description	Default
`notice`	Yes
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 14, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Although the annotations already cover safety (readOnly, idempotent, closed-world, non-destructive), the description adds substantial behavioral detail: the default open-tender filter, 10 results per page, the returned fields, and the meaning of knowledge.completeness (partial or listing_only tenders are still valid and not down-ranked). It also explains that filters_applied.sort_applied reports the actual order used.

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 description is dense but well ordered: purpose first, then default behavior, then routing alternatives, then return shape. Some sentences repeat schema content (status and record_kind widening the scope), and the return-value sentence is partly redundant with the output schema, but nothing is wasted.

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 an 11-parameter search tool with an output schema, the description covers what an agent needs: defaults, sibling routing, pagination, result fields, and a non-obvious data-quality signal (knowledge.completeness). Nothing required for correct invocation is missing.

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?

With 100% schema description coverage, the baseline is 3, but the description adds genuine meaning: query works best in Hebrew in the user's own words, category is more precise than free text for known topics, and status/record_kind widen the default scope. It does not, however, explain all 11 parameters, such as supplier_size or closes_by, beyond what the schema provides.

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?

The description opens with a specific verb and resource: 'Search Israeli public tenders in Tendy's catalog by free text and filters'. It then distinguishes this tool from siblings: browse_collection for overviews, list_categories for category discovery, and dedicated parameters for tender_number and publisher lookups.

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?

The description gives explicit routing rules: browse_collection handles category, publisher, region, or government/municipal overviews; tender_number and publisher serve direct lookups; category beats free text when the topic matches a list_categories entry. It also explains that the default open-only scope mirrors the Tendy website and how status and record_kind widen it.

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

All Tendy - Israeli public tenders tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.