Skip to main content
Glama

Request Image Upload

request_image_upload

Upload an image attached to the conversation — logos, photos, banners, anything the user has shown you. Returns a one-time URL the caller's runtime PUTs the raw bytes to (handles any size up to 50MB). Workflow: (1) call this tool, (2) PUT raw image bytes to the returned upload_url with Content-Type header (raw binary, NOT base64), (3) call finalize_image_upload with the returned asset_id. The URL expires in 5 minutes — issue this immediately before your PUT, not at the start of a long reasoning chain. JPEG/PNG/WebP only; no SVG. If the user is asking about photos they've already uploaded to their Zarla photo library, use list_site_photos first instead.

Annotations: read-only=false, destructive=false, idempotent=false, open-world=false. Why: Creates a one-time upload slot in Zarla's own storage; nothing existing changes (additive, not destructive). Not idempotent: each call creates another slot. Closed-world: the slot lives in Zarla's own storage — no third-party or user-controlled system is contacted.

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_id": "<site_id>",
      "mime": "<mime>"
    },
    "name": "request_image_upload"
  }
}

Input Schema

NameRequiredDescriptionDefault
altNoAccessibility alt text. Stored when finalize_image_upload returns.
mimeYesImage MIME type. JPEG/PNG/WebP only — SVG is not supported.
site_idYesThe site this image belongs to
byte_sizeNoOptional byte size for upfront cap check (max 50MB).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare non-read-only, non-destructive, non-idempotent, closed-world, and the description is consistent with each of those. Beyond the annotations it discloses non-obvious mechanics: the URL is one-time, expires in five minutes, must receive raw binary rather than base64, caps at 50MB, and the caller's runtime does the PUT while the tool only mints the slot.

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?

Purpose is front-loaded, then a numbered workflow, then format limits, then a routing note — a clean structure with almost no filler. The only minor redundancy is the parenthetical 50MB mention, which repeats the `byte_size` maximum already enforced by the schema.

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 tool with no output schema, the description compensates by naming the returned fields (`upload_url`, `asset_id`) and how they are consumed, so an agent knows what comes back. Combined with the expiry, format, and size constraints, nothing an agent needs to call it correctly 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 description coverage is 100%, so all four parameters are already documented, including the MIME enum, the 50MB cap on `byte_size`, and the note that `alt` is stored at finalize time. The description reinforces the format restrictions but adds no new per-parameter meaning such as defaults, edge cases, or interaction between `byte_size` and `mime` — the baseline 3 applies.

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 names a specific verb and resource (request an upload slot for an image attached to the conversation) and explicitly scopes what counts as input — 'logos, photos, banners, anything the user has shown you.' It also distinguishes itself from `finalize_image_upload` (the follow-up step) and `list_site_photos` (for already-uploaded library photos, not new ones).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives an explicit three-step workflow, states the negative condition for a sibling ('if the user is asking about photos they've already uploaded ... use list_site_photos first instead'), and rules out a case (SVG) that would otherwise cause a failed call. Timing guidance ('issue this immediately before your PUT, not at the start of a long reasoning chain') is exactly the kind of when-to-call information that prevents misuse.

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.