Skip to main content
Glama

Eurekuh

Upload a local file

upload_file

For a file on this machine with no public URL. Returns one signed upload URL per file (valid 2 hours) and the mediaId create_post takes. Upload each file yourself with: curl -fsS -X PUT -H "Content-Type: " --data-binary @ "" then pass the mediaIds to create_post. One call covers a carousel: count up to 10 images of one type, or a single video. create_post checks each file's real type and size (images up to 10MB, video up to 1GB, and each network's own lower limit) and refuses anything else. Uploading publishes nothing. If the file already has a public URL, use upload_media instead.

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": {
      "contentType": "<contentType>"
    },
    "name": "upload_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
countNoHow many files of this type. Default 1.
contentTypeYesThe files' type. Ask once per type if a carousel mixes jpeg and png.
organizationIdNoWhich organization to act in: an id from list_organizations. Leave out for this connection's default organization.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=true and idempotentHint=false, but the description adds genuinely non-obvious behavior: 'Uploading publishes nothing' (clarifying that a write-like tool has no public side effect), the 2-hour URL validity, the 10-image/single-video batch constraint, and that create_post re-validates real type and size. It does not cover re-invocation semantics (what happens if the same file is uploaded twice, despite idempotentHint=false) or whether unused URLs expire silently, so it stops short of the top band.

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 selection rule and the return value, then the operational curl recipe, then size limits. Almost every sentence earns its place, though the embedded multi-line curl command makes the prose block harder to scan and the type/size validation sentence is dense enough to need a second read.

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?

With no output schema, the description carries the burden of explaining returns and does so concretely: one signed upload URL per file valid 2 hours plus the mediaId create_post expects. It also documents enforcement limits (10MB images, 1GB video, per-network lower caps) and the fact that validation happens downstream, which is exactly what an agent needs to avoid a failed create_post.

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. The description adds meaning beyond the schema by linking count to the batch model ('count up to 10 images of one type, or a single video') and tying contentType to the mixed-carousel case, which is otherwise only in the schema's own text. It says nothing extra about organizationId, but the schema already handles that default clearly.

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 opens with a precise scope — 'a file on this machine with no public URL' — and states both what the tool produces (one signed upload URL per file, valid 2 hours, plus the mediaId) and what it hands off to create_post. It explicitly distinguishes itself from the near-identically named sibling upload_media by URL availability, so an agent can route between them without opening either 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?

Both branches are stated: use this tool when the file is local with no public URL, use upload_media when it already has a public URL. It also gives the downstream sequencing ('then pass the mediaIds to create_post') and the batching rule ('one call covers a carousel: count up to 10 images of one type, or a single video'), leaving nothing to inference.

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