Skip to main content
Glama

Recall Kitchen

by io.github.adamdecaf

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, costco, target, walmart), 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
NameRequiredDescriptionDefault
limitNonumber of recalls to return, 1-100, default 3
queryNowebsearch query: unquoted words are AND, OR is or, -term excludes, quoted phrases match as a unit. Example: Generac Generator -Portable
sinceNooptional published-on start date YYYY-MM-DD
untilNooptional published-on end date YYYY-MM-DD
offsetNonumber of recalls to skip
sourceNooptional 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.
locationNooptional country, region, or place; ANDed with the query. US aliases such as CA and California still apply

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
offsetYes
recallsYes
nextOffsetNo

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnly/openWorld/idempotent/destructive-safe behavior, so the bar is lower. The description adds useful behavioral context beyond those hints: result descriptions are truncated, extracted products are capped, and location is ANDed with the query. This is meaningful operational detail an agent needs to interpret results correctly.

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?

The description is dense but every sentence earns its place: purpose, query syntax with example, filters, caveat about truncation, and pointer to the full-text sibling. It is front-loaded with the core purpose and uses compact but precise wording.

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?

With 7 parameters, a 100% schema-coverage schema, an output schema, and no nested objects, the description covers everything an agent needs for correct invocation: syntax, filters, aliases, truncation behavior, and the alternative for full text. Nothing critical 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?

Schema coverage is 100%, giving a baseline of 3. The description adds significant extra meaning beyond the schema: websearch syntax rules, source aliases (FDA, medwatch, vehicle, sams), and the ANDing behavior of location. This is more than a restatement of parameter names and helps the agent use the parameters correctly.

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 states a specific verb and resource ('Search product recalls by query') and clarifies the query mechanism, including syntax and examples. It also differentiates from siblings by noting that full text is available via get_product_recall, and its title distinguishes it from search_product_recalls_by_upc and search_product_recalls_from_image.

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?

The description gives concrete guidance on how to construct queries, available filters, source values, and date/location options. It explicitly directs the agent to get_product_recall for full text when descriptions are truncated, which is a clear alternative-selection cue. It does not explicitly contrast with UPC/image/identifier search siblings, but the query-based nature is clearly implied.

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

All Recall Kitchen toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0
Disambiguation4/5

Most tools have clear, distinct resource-action boundaries (inventory vs. watch patterns vs. notifications vs. search). The search tools overlap somewhat—especially search_product_recalls_by_upc, search_product_recalls_from_image, and search_recalls_by_identifier—but their input types and intent are described well enough to avoid major confusion.

Naming Consistency4/5

The overwhelming majority follow a predictable verb_noun snake_case pattern (add_inventory_product, list_watch_patterns, revoke_api_key). Minor deviations like signup, list_inventory, and search_recalls_by_identifier (instead of search_product_recalls_by_identifier) keep it from being perfectly consistent.

Tool Count4/5

With 19 tools, the server is slightly on the heavier side, but the count is justified by covering several distinct areas: account/key management, inventory, watch patterns, recall search, and notifications. Each tool appears to serve a real purpose, though a few search variants could arguably be consolidated.

Completeness4/5

The set covers the core lifecycle well: signup, key management, inventory and watch pattern add/list/remove, multiple recall search paths, recall detail lookup, and notification read state. Minor gaps exist, such as no update operation for inventory items or watch patterns and no bulk notification actions, but agents can work around these.

Resources