Skip to main content
Glama

Hail Communication for AI

Create a file upload link

create_file_upload

Create a one-time link that uploads one file from a shell with curl.

    The bytes go from the local disk to Hail directly, not through the tool call,
    so any file that is not tiny goes this way.
    An email attachment can be up to 25 MB. A verification document must be
    JPG, PNG or PDF, up to 10 MB, and is usable for 1 hour after the upload.
    Returns ``id``, ``upload_url``, ``expires_at`` (15 minutes), ``max_bytes``
    and a ready ``curl`` line with a ``'FILE_PATH'`` placeholder for the
    file's absolute path.
    The link needs no key and works once. The upload response holds
    ``size_bytes`` and ``sha256`` to compare with the local file.

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": {
      "purpose": "<purpose>",
      "filename": "<filename>",
      "content_type": "<content_type>"
    },
    "name": "create_file_upload"
  }
}

Input Schema

NameRequiredDescriptionDefault
purposeYesWhat the file is for. ``email_attachment``: its ``id`` goes in ``send_email``'s ``attachment_ids``. ``verification_document``: its ``id`` goes in the ``files`` of ``check_verification`` and ``submit_verification`` as ``{slot, upload_id}``.
filenameYesFile name, such as ``passport.pdf``.
llm_modelNoModel ID of the calling agent. Optional. Recorded for analytics only.
content_typeYesThe file's MIME type, such as ``application/pdf``.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / llm_model
      Added value: +{
      +  "description": "Model ID of the calling agent. Optional. Recorded for analytics only.",
      +  "type": "string"
      +}
  2. Changed2 schema fields changed
    • changedInput schema / properties / purpose / description
      Previous value: -"``email_attachment`` (25 MB at most; the ``id`` works in ``send_email``'s ``attachment_ids``) or ``verification_document`` (JPG, PNG or PDF, 10 MB at most; ``{slot, upload_id}`` works in the ``files`` of ``check_verification`` and ``submit_verification`` for 1 hour after the upload)."New value: +"What the file is for. ``email_attachment``: its ``id`` goes in ``send_email``'s ``attachment_ids``. ``verification_document``: its ``id`` goes in the ``files`` of ``check_verification`` and ``submit_verification`` as ``{slot, upload_id}``."
    • addedInput schema / properties / purpose / enum
      Added value: +[
      +  "email_attachment",
      +  "verification_document"
      +]
  3. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only say readOnly=false, idempotent=false, destructive=false; the description goes much further by disclosing that the link is single-use, requires no key, expires in 15 minutes, and that the verification variant is usable for only 1 hour after upload. It also explains post-upload verification via size_bytes and sha256, which an agent could not infer from 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, then constraints, then return shape, so a reader can stop early. Slightly long with some formatting noise (double-backticks, a mid-paragraph line break), but no sentence is redundant.

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 link-creation tool with an output schema, an agent needs the lifecycle (single-use, 15-minute link), the size/format ceilings per purpose, and how the resulting id is consumed downstream. All of that is present, so nothing essential is left to inference.

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 real constraints tied to parameters: the 25 MB email-attachment ceiling, the JPG/PNG/PDF and 10 MB limits for verification documents, and the 'FILE_PATH' placeholder expected in the returned curl line. That meaningfully narrows how purpose and content_type should be chosen.

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 specific verb and resource ('Create a one-time link that uploads one file') and immediately frames the mechanism ('from a shell with curl'), which cleanly separates it from an in-call upload path. An agent can tell what this produces (a link, not a file) without opening the schema.

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 a usable selection heuristic: 'The bytes go from the local disk to Hail directly, not through the tool call, so any file that is not tiny goes this way,' plus per-purpose size and format limits. It stops short of naming a sibling upload tool explicitly, so the alternative is implied rather than 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