Skip to main content
Glama
Sign In

PageHub

by dev.pagehub
OverviewDiscussionsAdmin

Upload file

upload_file

Upload any plan-allowed file. Images go to the CDN; video/audio/pdf/zip go to R2. Returns a mediaId: {{ '' | file_url }} works in an , , or a collection url/media field (images: {{ '' | image_url: width: 800 }}). Web files: fileUrl. dataBase64 is a last resort (~3MB cap; pass mimeType for non-images).

Input Schema

NameRequiredDescriptionDefault
idNoSite id.
fileUrlNoPublic URL of the original file — no resize params.
privateNoStore privately for set_download (any type; no public url). Needs filePath.
filenameNoFilename hint.
mimeTypeNoRequired with dataBase64 for non-images, e.g. video/mp4, application/pdf.
dataBase64NoBase64 of a real file's bytes, never base64 you write out (it arrives cut off). ~3MB cap; prefer imageUrl.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / dataBase64 / description
      Previous value: -"Base64 or data URL. Last resort: ~3MB cap."New value: +"Base64 of a real file's bytes, never base64 you write out (it arrives cut off). ~3MB cap; prefer imageUrl."
  2. Changed1 schema field changed
    • addedInput schema / properties / private
      Added value: +{
+  "description": "Store privately for set_download (any type; no public url). Needs filePath.",
+  "type": "boolean"
+}
  3. Changed1 schema field changed
    • changedInput schema / properties / id / description
      Previous value: -"Site id. Pass it on every call."New value: +"Site id."
  4. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations only say non-read-only, non-idempotent, open-world, non-destructive; the description adds the meaningful behavior — where bytes are stored, what identifier comes back, and the base64 size ceiling. The `private`/set_download path is left to the schema and the phrase 'plan-allowed' is undefined, which keeps this from a 5.

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 purpose and routing, then moves to the return value and per-input guidance. Dense but nearly every clause carries information; the inline template expressions are the only noisy part.

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?

With no output schema, the description correctly takes on return-value duty by naming both `mediaId` and `fileUrl` and showing where each is usable. What remains thin is the `private`/set_download workflow and the meaning of 'plan-allowed', neither of which is spelled out.

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, and the description adds usable meaning on top: `fileUrl` is for the original unresized file, `dataBase64` is a fallback with a cap, `mimeType` pairs with base64 for non-images. The mismatched 'imageUrl' reference is the one blemish.

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?

Clear verb+resource ('Upload any plan-allowed file') plus a concrete storage-routing rule (images→CDN, video/audio/pdf/zip→R2) and the returned handle. It is distinguishable in substance from the sibling upload_image, but it never names that sibling, so an agent must infer which tool to pick for images.

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?

Gives real selection guidance among inputs: use `fileUrl` for web files, `dataBase64` only as a last resort with a ~3MB cap and a required mimeType for non-images. It stops short of stating when to prefer upload_image or set_download instead, and 'prefer imageUrl' references a parameter name that does not exist in the schema (the field is `fileUrl`).

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

All PageHub toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources