Skip to main content
Glama

bulk_put_assets

DestructiveIdempotent

Upload 1–200 CMS assets; key = path after /assets/, or sitePath for an exact URL path (e.g. /.well-known/security.txt, /ads.txt). Each item: exactly one of bodyBase64, bodyText (plain text for .css/.js/.mjs/.json/.svg/.txt/.xml only — not .html pages), or importFromUrl. Optional bodySha256 checks the sent bytes; response sha256 = stored bytes (WebP may differ). JPEG/PNG/static GIF are re-encoded to WebP (response key photo.webp; /assets/photo.jpg keeps serving it) — use the response key in CSS/JS; optimize:false stores the bytes as sent at your key; animated GIFs are always kept. Live in the editor and draft preview at once; on the published site after the next publish.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "site": "<site>",
      "items": "<items>"
    },
    "name": "bulk_put_assets"
  }
}

Input Schema

NameRequiredDescriptionDefault
siteYesSite slug, e.g. acme-studio
itemsYes
contextNoWhy you're calling this (activity log).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • removedInput schema / $schema
      Removed value: -"http://json-schema.org/draft-07/schema#"
    • changedInput schema / properties / context / description
      Previous value: -"Optional: one sentence on why you are calling this (shown in the site's activity log; no personal data)."New value: +"Why you're calling this (activity log)."
  2. Changed3 schema fields changed
    • changedInput schema / properties / context / description
      Previous value: -"One sentence: why you are calling this tool and what you are trying to accomplish. Stored on the site's activity log and visible to everyone on the site — never put secrets or personal data here."New value: +"Optional: one sentence on why you are calling this (shown in the site's activity log; no personal data)."
    • removedInput schema / properties / guestToken
      Removed value: -{
      -  "description": "Guest token from start_site. Send it on every call until claim_site. Omit when this chat is already signed in to Dotsy.",
      -  "minLength": 20,
      -  "type": "string"
      -}
    • changedInput schema / required
      Previous value: -[
      -  "site",
      -  "items",
      -  "context"
      -]New value: +[
      +  "site",
      +  "items"
      +]
  3. Changed2 schema fields changed
    • addedInput schema / properties / items / items / properties / sitePath
      Added value: +{
      +  "description": "Store at this exact site path instead of /assets/{key} — e.g. /.well-known/security.txt, /ads.txt, /favicon.ico. Send key OR sitePath.",
      +  "type": "string"
      +}
    • removedInput schema / properties / items / items / required
      Removed value: -[
      -  "key"
      -]
  4. Changed1 schema field changed
    • addedInput schema / properties / items / items / properties / optimize
      Added value: +{
      +  "description": "Default true: a JPEG, PNG or static GIF is re-encoded to WebP (key photo.jpg is stored as photo.webp, and /assets/photo.jpg still serves it). false stores the bytes exactly as sent, at the key given. Animated GIFs are always kept as sent.",
      +  "type": "boolean"
      +}
  5. Changed1 schema field changed
    • addedInput schema / properties / items / items / properties / bodyText
      Added value: +{
      +  "type": "string"
      +}
  6. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Well above the annotation baseline: the description discloses the WebP re-encode pipeline, the returned key differing from the requested key with the old path still serving, that optimize:false bypasses re-encoding, that animated GIFs are exempt, the sha256-mismatch abort happening before any write, and the editor/draft-versus-published timing. The one notable omission on a destructiveHint=true, idempotentHint=true tool is that overwriting an existing key is what makes it destructive and idempotent — that is never said.

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?

Front-loaded with the operation and bounds, then the addressing rules, then encoding behaviour, then publish timing — a sensible order. It is dense but nearly every clause carries a real constraint. Small waste from repeating the editor/draft/publish note already present in the `key` schema description, and heavy em-dash nesting makes it harder to scan than it needs to be.

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 non-read-only, destructive, idempotent bulk-write tool with no output schema and three top-level parameters, this covers the essentials an agent needs: batch limits, addressing modes, body source exclusivity, transform side effects on keys, integrity checking, and propagation timing. The remaining gap is overwrite semantics — whether putting an existing key replaces it silently — which matters given destructiveHint=true.

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 67%, so the description needs to compensate somewhat, and it does the highest-value thing the schema cannot: it declares the mutual exclusivity ('exactly one of bodyBase64, bodyText, or importFromUrl') and the bodyText extension whitelist including the .html exclusion. It restates some schema-documented behaviour (optimize, sitePath, bodySha256) rather than adding to it, and leaves `intent` and `contentType` unexplained in both places.

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?

The description leads with a specific verb and resource plus a hard bound: 'Upload 1–200 CMS assets', and immediately defines the addressing scheme (key = path after /assets/, or sitePath). That is far more than a restatement of the name. It stops short of 5 because it never contrasts itself with the sibling content-writing tools (bulk_put_content / put_content), so the asset-vs-page boundary is only implied by the resource noun.

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?

Guidance is entirely at the item level — exactly one of bodyBase64/bodyText/importFromUrl, key-versus-sitePath, and bodyText being unsuitable for .html pages — which implicitly pushes HTML pages elsewhere. There is no explicit when-to-use-this-instead-of-X statement naming an alternative tool, and no note about how this differs from the singular asset workflow. Usage is inferable but not stated.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources