get_media_urlsFetch public media links (PDF, EPUB, MP3, image, markdown) for an item, including MIME type and size when known. Filter by kind or return all kinds.
Public media URLs for an item (pdf, epub, mp3, image, markdown), with MIME type and size when known. The server does not proxy bytes. kinds filters the list; omit it for every kind on the item.
| Name | Required | Description | Default |
|---|---|---|---|
| kinds | No | ||
| item_id | Yes |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, yet the description still adds real behavioral context: no byte proxying (the caller must fetch the URL itself) and that MIME type and size are returned only 'when known'. It does not mention auth requirements or ordering of results.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three short sentences, no filler, and the return-shape information is front-loaded ahead of the parameter note. Every sentence carries distinct information (what is returned, what is not provided, how to filter).
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description correctly carries the burden of describing the return (URLs plus MIME type and size when known), which is the essential information for a read-only lookup tool. Minor gaps: no note on result ordering, empty-result behavior, or whether URLs expire.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate — and it does for 'kinds': it lists the accepted kinds and, crucially, discloses the default behavior when omitted ('omit it for every kind'), which the schema does not. It never mentions 'item_id' or its expected format, leaving one of two parameters undocumented.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Public media URLs for an item') and enumerates the concrete kinds returned, so an agent immediately knows this retrieves links rather than content. It does not explicitly contrast with the closest sibling (get_item), but the resource is specific enough to be distinguishable.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is implied rather than stated: 'The server does not proxy bytes' tells the agent this yields URLs for client-side fetching, but there is no explicit when-to-use or when-to-prefer-an-alternative guidance versus get_item or search_content. Adequate but with a clear gap.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.