mcp-walmart-ads

Overview Schema Source Related Servers Discussions Admin

download_file

Idempotent

Download Walmart Connect reports, labels, and display snapshots by URL, operation ID, or API method and path; writes to a path or caches the uncompressed payload.

Instructions

[Walmart] Download a report, label, or snapshot. Give a full url — such as the details URL from a display snapshot poll, or a Marketplace report url — or an operation_id, or an api with method and path. Written to dest_path when given, otherwise gunzipped and cached. Redirects are followed for you.

Input Schema

TableJSON Schema

Name	Required	Description
`api`	No	Api to call when using method+path. Src: platforms.
`url`	No	Absolute URL to fetch, e.g. a snapshot or report URL returned by a previous call.
`path`	No	API path when not using url.
`method`	No	HTTP method when using path. Defaults to GET.
`params`	No	Query string parameters as a JSON object.
`region`	Yes	Region label, e.g. us. Src: platforms.
`tenant`	No	WAP tenant for non-US walmart:ads regions. Sent as wap-tenant-id.
`platform`	No	Platform to authenticate as. Required with a bare url; otherwise inferred from operation_id or api. Src: platforms.
`dest_path`	No	Local path to write the bytes to. Omit to gunzip and cache the payload instead, readable at the returned cached_at resource.
`environment`	Yes	Target environment. walmart:marketplace accepts production or sandbox; the ads platforms accept whatever the config declares, usually production or staging. Src: platforms.
`path_params`	No	Values for {placeholders} in path.
`operation_id`	No	Operation id, qualified or bare. Src: operations.
`advertiser_id`	No	Required on walmart:marketplace (selects the credential) and by display snapshot downloads, where it is sent as X-Advertiser-ID and as the advertiserId query parameter. Src: platforms.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`path`	No
`urls`	No
`error`	No
`cached_at`	No
`size_bytes`	No
`status_code`	No
`content_type`	No
`bytes_written`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.4.0Sep 11, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false) leave the mutation oddity unexplained, and the description resolves it by disclosing the actual behavior: bytes are written to dest_path when given, otherwise gunzipped and cached, with redirects followed automatically. It stops short of stating auth/permission requirements, which the schema carries instead.

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 tight sentences, front-loaded with the verb and resource, then the input modes, then the output behavior. No filler; only minor loss for packing several clauses into the middle sentence.

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

Completeness4/5

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

For a 13-parameter tool with an output schema (so return values need no explanation), the description covers the targeting modes and the write-vs-cache outcome adequately. The remaining gap is the absence of sibling routing against call_endpoint.

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 already 100%, so the baseline is 3, but the description adds real meaning by showing the three mutually exclusive targeting modes (url vs operation_id vs api+method+path) and giving concrete examples of the URLs that work. It does not add syntax detail for params/tenant/path_params 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: 'Download a report, label, or snapshot', with the scope prefixed by '[Walmart]'. It is clear what the tool fetches, but it never distinguishes itself from the sibling call_endpoint, which likely also retrieves remote data.

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 description explains the three input modes (full url, operation_id, or api with method and path) which implies usage, but gives no explicit when-to-use/when-not guidance and never names call_endpoint or any sibling as the alternative for a given case.

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

Deploy Server