Recall Kitchen

search_product_recalls

Read-onlyIdempotent

Search product recalls by query. Query uses websearch syntax: unquoted words are AND, OR is or, -term excludes, quoted phrases match as a unit (example: Generac Generator -Portable). Optional filters: source (cpsc, fdafoodsafety, FDAMedWatch, usda, nhtsa, canada, costco, target, walmart, openfda), since/until (YYYY-MM-DD), location (country, region, or place, ANDed with the query), offset, limit. Descriptions are truncated and extracted products are capped; use get_product_recall for the full text.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	number of recalls to return, 1-100, default 3
`query`	No	websearch query: unquoted words are AND, OR is or, -term excludes, quoted phrases match as a unit. Example: Generac Generator -Portable
`since`	No	optional published-on start date YYYY-MM-DD
`until`	No	optional published-on end date YYYY-MM-DD
`years`	No	optional published window in years (1-50). Ignored when since is set
`offset`	No	number of recalls to skip
`source`	No	optional source filter: cpsc, fdafoodsafety, FDAMedWatch, usda, nhtsa, canada, costco, target, walmart, or openfda. Aliases: FDA and food map to fdafoodsafety; medwatch maps to FDAMedWatch; vehicle, vin, and car map to nhtsa; healthcanada, cfia, and hc-sc map to canada; sams maps to walmart; enforcement, res, and fdaenforcement map to openfda. For more than one source, pass sources.
`sources`	No	optional sources to include (OR). Same values as source
`location`	No	optional country, region, or place; ANDed with the query. USA, Canada, Mexico, EU, and Europe match places in that region. CA is California, not Canada.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`offset`	Yes
`recalls`	Yes
`nextOffset`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedSep 9, 2026

changedInput schema / properties / source / description

Previous value: -"optional source filter: cpsc, fdafoodsafety, FDAMedWatch, usda, nhtsa, costco, target, or walmart. Aliases: FDA and food map to fdafoodsafety; medwatch maps to FDAMedWatch; vehicle, vin, and car map to nhtsa; sams maps to walmart. For more than one source, pass sources."New value: +"optional source filter: cpsc, fdafoodsafety, FDAMedWatch, usda, nhtsa, canada, costco, target, walmart, or openfda. Aliases: FDA and food map to fdafoodsafety; medwatch maps to FDAMedWatch; vehicle, vin, and car map to nhtsa; healthcanada, cfia, and hc-sc map to canada; sams maps to walmart; enforcement, res, and fdaenforcement map to openfda. For more than one source, pass sources."

changedInput schema / properties / source / enum

Previous value: -[
-  "cpsc",
-  "fdafoodsafety",
-  "FDAMedWatch",
-  "usda",
-  "nhtsa",
-  "costco",
-  "target",
-  "walmart"
-]New value: +[
+  "cpsc",
+  "fdafoodsafety",
+  "FDAMedWatch",
+  "usda",
+  "nhtsa",
+  "canada",
+  "costco",
+  "target",
+  "walmart",
+  "openfda"
+]

changedInput schema / properties / sources / items / enum

Previous value: -[
-  "cpsc",
-  "fdafoodsafety",
-  "FDAMedWatch",
-  "usda",
-  "nhtsa",
-  "costco",
-  "target",
-  "walmart"
-]New value: +[
+  "cpsc",
+  "fdafoodsafety",
+  "FDAMedWatch",
+  "usda",
+  "nhtsa",
+  "canada",
+  "costco",
+  "target",
+  "walmart",
+  "openfda"
+]

Changed1 schema field changedSep 9, 2026

changedInput schema / properties / location / description

Previous value: -"optional country, region, or place; ANDed with the query. US aliases such as CA and California still apply"New value: +"optional country, region, or place; ANDed with the query. USA, Canada, Mexico, EU, and Europe match places in that region. CA is California, not Canada."

Changed3 schema fields changedSep 9, 2026

changedInput schema / properties / source / description

Previous value: -"optional source filter: cpsc, fdafoodsafety, FDAMedWatch, usda, nhtsa, costco, target, or walmart. Aliases: FDA and food map to fdafoodsafety; medwatch maps to FDAMedWatch; vehicle, vin, and car map to nhtsa; sams maps to walmart."New value: +"optional source filter: cpsc, fdafoodsafety, FDAMedWatch, usda, nhtsa, costco, target, or walmart. Aliases: FDA and food map to fdafoodsafety; medwatch maps to FDAMedWatch; vehicle, vin, and car map to nhtsa; sams maps to walmart. For more than one source, pass sources."

addedInput schema / properties / sources

Added value: +{
+  "description": "optional sources to include (OR). Same values as source",
+  "items": {
+    "enum": [
+      "cpsc",
+      "fdafoodsafety",
+      "FDAMedWatch",
+      "usda",
+      "nhtsa",
+      "costco",
+      "target",
+      "walmart"
+    ],
+    "type": "string"
+  },
+  "type": "array",
+  "uniqueItems": true
+}

addedInput schema / properties / years

Added value: +{
+  "description": "optional published window in years (1-50). Ignored when since is set",
+  "maximum": 50,
+  "minimum": 1,
+  "type": "integer"
+}

First observedSep 6, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, openWorldHint, non-destructive), so the description correctly focuses on adding behavior beyond that: the truncation/capping of results, the websearch AND/OR/exclusion/quoted-phrase semantics, and the aliasing behavior. It does not contradict any annotation.

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 sentences, purpose front-loaded, followed by a concrete syntax example, the filter summary, and the truncation/alternate-tool note. Every sentence earns its place and the most important routing information (use get_product_recall for full text) is clearly flagged. Dense but efficient.

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 9-parameter search tool with a rich output schema and a fully covered safety profile from annotations, the description is complete: it covers query syntax, filters, date windows, aliasing, the results-truncation caveat, and the fallback tool. Nothing an agent needs to call it correctly or decide whether to escalate is missing.

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%, so all 9 parameters carry their own descriptions. The description adds marginal value by front-loading the source filter options and illustrating the query syntax with an example ('Generac Generator -Portable'), but it largely restates what the schema already documents (since/until format, location semantics, offset/limit), so the baseline of 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?

The description opens with 'Search product recalls by query,' naming a specific verb, resource, and search modality. The query-based nature distinguishes it from the sibling tools search_product_recalls_by_upc, search_product_recalls_from_image, and search_recalls_by_identifier, and it explicitly names get_product_recall as the companion for full text, giving the agent a clear map of the family.

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?

It gives an explicit routing rule: 'Descriptions are truncated and extracted products are capped; use get_product_recall for the full text,' telling the agent exactly when to escalate. It stops short of naming the alternative search siblings (by UPC, by image, by identifier) and stating when to prefer them over a query, which would make the guidance fully complete.

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

All Recall Kitchen 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.