Skip to main content
Glama

Upload a proof screenshot

upload_proof_screenshot

Store a screenshot the user gave you as proof (for tasks whose proof is a screenshot, e.g. a closed Slack). Returns screenshot_url → pass it to submit_campaign_work with task_id. PNG / JPG / WebP / GIF, 5 MB max; a blank image is refused. Free.

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": {
      "campaign_id": "<campaign_id>",
      "image_base64": "<image_base64>",
      "content_type": "<content_type>"
    },
    "name": "upload_proof_screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
file_nameNo
campaign_idYes
content_typeYes
image_base64YesThe image as base64 (a data: URL also works)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior4/5

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

Annotations only say it is a non-destructive write; the description adds real context on top: accepted formats, a 5 MB cap, that blank images are rejected, that it costs nothing ('Free'), and that it returns screenshot_url. It does not address idempotency (annotations say idempotentHint=false) or what happens if the same screenshot is uploaded twice, which is the one gap for a write tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences: the purpose and scope come first, then the return value and the next-step handoff, then the constraints. Every clause carries information an agent needs and nothing is repeated from the schema or annotations.

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 4-parameter write tool with no output schema, the description covers purpose, input constraints, return value and downstream usage, which is nearly everything needed. Minor omissions remain: whether campaign_id must reference an existing campaign and whether the returned URL is persistent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 25% — image_base64 is documented, but campaign_id, content_type and file_name are not. The description's format list (PNG / JPG / WebP / GIF) maps loosely onto the content_type enum and hints that content_type must match the payload, but campaign_id and file_name get no explanation, so the compensation for the low coverage is partial.

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 ('Store a screenshot ... as proof') plus the qualifying condition ('for tasks whose proof is a screenshot, e.g. a closed Slack'). It also positions itself relative to submit_campaign_work by naming it as the downstream consumer, so an agent can tell the two apart 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 Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The condition 'for tasks whose proof is a screenshot' tells the agent when this tool applies, and the follow-up instruction ('pass it to submit_campaign_work with task_id') gives the correct sequencing. It stops short of stating when NOT to use it or naming the alternative proof-submission path for non-screenshot tasks.

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.