Skip to main content
Glama
Sign In

Invoke Human Tool

by com.invokehumantool
OverviewDiscussionsAdmin

Upload a video

upload_video
Idempotent

Store an MP4 on this account and return its vid_ id. Pass data_base64. alt is optional. The type is sniffed from the bytes. The limit is 8 MB and 20 seconds. The same bytes on this account return the same video_id. Reference that id on a video block. An https URL is rejected. POST /videos sends those bytes as the raw body, with alt as a query parameter. This does not send a handoff.

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": {
      "data_base64": "<data_base64>"
    },
    "name": "upload_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
altNoShort description stored with the video. At most 200 characters.
data_base64YesBase64-encoded MP4. At most 8 MB and 20 seconds decoded.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations it discloses hard limits (8 MB, 20 seconds decoded), content sniffing, and the dedup rule that identical bytes map to the same video_id — a concrete elaboration of idempotentHint=true. It also explicitly denies a side effect ("does not send a handoff"), which matters given the many handoff siblings. The only weak spot is the raw-body/query-parameter transport note, which is HTTP-level detail rather than agent-facing behavior.

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, required parameter, limits, and side-effect disclaimers are front-loaded in short declarative sentences with no filler. The telegraphic style makes it scannable. One sentence about POST /videos raw body and query parameters is transport trivia that does not help an MCP caller.

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?

For a two-parameter tool with no output schema, it covers purpose, input format, constraints, return identifier, and downstream usage. The one substantive ambiguity is whether a re-upload of identical bytes with a different alt returns the prior id or overwrites the caption. That is a small but real gap for a deduplicating write tool.

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, but the description adds real meaning: it stresses data_base64 must be actual bytes rather than an https URL, and notes the format is sniffed rather than declared. That closes the most likely misuse path. It does not clarify whether alt participates in the dedup identity.

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 first sentence gives a concrete verb and resource plus the return contract: "Store an MP4 on this account and return its vid_ id." It also disambiguates from the handoff family with "This does not send a handoff" and from URL-based ingestion with "An https URL is rejected." An agent can identify this as the byte-upload path 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?

It supplies clear preconditions: pass base64 bytes, an https URL is rejected, and the id is consumed by a video block. The negative guidance (no URLs, no handoff) is genuinely useful routing information. It stops short of naming a sibling it substitutes for (e.g. upload_image vs. import_image_url) by name, so it is clear but not fully comparative.

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

All Invoke Human Tool 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