Skip to main content
Glama

SnapHost

by ai.snaphost
OverviewDiscussionsAdmin

Upload bundle part

upload_bundle_part
Idempotent

Send one numbered slice of a .zip, or of a single non-zip file, into an upload opened by create_bundle_upload, encoded as base64 in this call. This is the route that needs no network beyond the one carrying this tool call, so it is how a sandboxed client publishes a multi-file bundle or a lone Markdown, notebook, PDF, Word, PowerPoint, Excel, image, video, audio, CSV, Mermaid or text file. Split the file into slices of at most 1048576 bytes, base64 each slice on its own, and send them as part 0, 1, 2, ... with no gaps; part 0 must be the opening bytes of the archive unless filename names a single non-zip file. Nothing is published until publish_site or update_site is called with the upload_id, which joins the parts in index order and verifies the bytes, so a rejected or damaged part costs only that part: send that index again, the others still stand. Re-sending an index replaces it. Pass the same workspace_id as create_bundle_upload did.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
partYes0-based index of this slice in the .zip, sent in order and with no gaps
filenameNoThe single file's own name (`report.pdf`), when the upload is one non-zip file rather than a .zip; part 0 is then not expected to begin an archive. Pass the same name to publish_site / update_site.
upload_idYesThe `upload_id` from create_bundle_upload
partBase64YesThis slice of the file, base64-encoded. It is a slice, not a file of its own, and every slice but the first is meaningless alone. Read it from the encoded file verbatim rather than reproducing it from memory.
workspace_idNoOptional: the workspace to act in, from list_workspaces (the connection reaches the person's personal space and every workspace they are a member of). Required on a write when the connection reaches more than one workspace. Omit to act in the personal space (for an older single-workspace connection, the one workspace it was authorized for).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / filename
      Added value: +{
+  "description": "The single file's own name (`report.pdf`), when the upload is one non-zip file rather than a .zip; part 0 is then not expected to begin an archive. Pass the same name to publish_site / update_site.",
+  "type": "string"
+}
    • changedInput schema / properties / partBase64 / description
      Previous value: -"This slice of the .zip, base64-encoded. It is a slice of the archive, not an archive of its own, and every slice but the first is meaningless alone. Read it from the encoded file verbatim rather than reproducing it from memory."New value: +"This slice of the file, base64-encoded. It is a slice, not a file of its own, and every slice but the first is meaningless alone. Read it from the encoded file verbatim rather than reproducing it from memory."
  2. Changed1 schema field changed
    • changedInput schema / properties / workspace_id / description
      Previous value: -"Optional: the workspace (the personal space or a Pro workspace) to act in, from list_workspaces. Omit to act in the token owner's own account."New value: +"Optional: the workspace to act in, from list_workspaces (the connection reaches the person's personal space and every workspace they are a member of). Required on a write when the connection reaches more than one workspace. Omit to act in the personal space (for an older single-workspace connection, the one workspace it was authorized for)."
  3. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare non-readOnly, idempotent, non-destructive, closed-world, but the description goes further: nothing publishes until publish_site/update_site runs, a rejected/damaged part costs only that part, re-sending an index replaces it, and the same workspace_id must be reused. That is genuine failure/recovery and state semantics beyond the annotations.

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 core action and the routing rationale, and every sentence carries operational content (slicing rule, ordering, publish gate, error recovery). It is, however, one dense paragraph that could be split for scanning; slight verbosity keeps it off a 5.

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?

There is no output schema, but the description covers validation (bytes verified at publish), failure handling, ordering, the filename/zip distinction, and workspace consistency. An agent has everything needed to call this multi-part writer correctly.

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 100%, so the baseline is 3, but the description adds cross-parameter constraints the schema does not: slices must be base64'd individually, sent as 0,1,2 with no gaps, and part 0 must be the archive's opening bytes unless filename names a lone non-zip file. It also ties workspace_id to create_bundle_upload.

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?

States a precise verb+resource: 'Send one numbered slice of a .zip, or of a single non-zip file, into an upload opened by create_bundle_upload.' It names the opening sibling and the exact artifact being uploaded, so an agent can distinguish it from create_bundle_upload and publish_site without opening any schema.

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?

Explicitly says when to use it ('the route that needs no network beyond the one carrying this tool call, so it is how a sandboxed client publishes...') and names the siblings that bracket the workflow (create_bundle_upload opens, publish_site/update_site finish). Nothing is left to inference.

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

All SnapHost 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