Skip to main content
Glama

Submit campaign participation proof

submit_campaign_work

Submit the user's work for a campaign. Three ways to prove it, and any one is enough: proof_url (content they published or an action they took), media_url (a hosted image or video made for the task — the ad-hoc creative case: a demo clip, a mockup, a designed asset), and description (max 500 chars). Media must already be hosted somewhere public and reachable — this API takes links, never uploads; a direct image link is shown to the reviewer inline, anything else (a video, a Loom) is shown as a link they open. If a URL is an X post it must be published by the user's linked X handle (author-verified); other URLs are accepted as-is. Lands as PENDING — the campaign owner reviews and rewards ship on approval (community campaigns pay Stars, public ones leaderboard points). Duplicate URLs are rejected. Check status afterward with get_my_submissions. ACTION CAMPAIGNS (get_campaign_brief shows kind 'action_tasks' and a tasks list): pass task_id — an exclusive task must be claimed first (claim_task) — and the proof the task asks for: proof_url (a link to the post / listing / comment) and/or screenshot_url (from upload_proof_screenshot).

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>"
    },
    "name": "submit_campaign_work"
  }
}

Input Schema

NameRequiredDescriptionDefault
task_idNoAction campaigns only (required there): the task this proof is for
media_urlNoPublic URL of an image or video produced for the task. Must already be hosted (upload it wherever the user keeps files first) — direct image links render inline for the reviewer; videos and Loom-style links show as a link.
proof_urlNoURL of the published content or action proof (X post, video, voting page, …)
campaign_idYes
descriptionNoWhat was done, or context for the reviewer
screenshot_urlNoAction campaigns: a screenshot from upload_proof_screenshot

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / screenshot_url
      Added value: +{
      +  "description": "Action campaigns: a screenshot from upload_proof_screenshot",
      +  "format": "uri",
      +  "type": "string"
      +}
    • addedInput schema / properties / task_id
      Added value: +{
      +  "description": "Action campaigns only (required there): the task this proof is for",
      +  "type": "string"
      +}
  2. Changed1 schema field changed
    • addedInput schema / properties / media_url
      Added value: +{
      +  "description": "Public URL of an image or video produced for the task. Must already be hosted (upload it wherever the user keeps files first) — direct image links render inline for the reviewer; videos and Loom-style links show as a link.",
      +  "format": "uri",
      +  "type": "string"
      +}
  3. Added

TDQS

A4.2/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing the resulting state (lands as PENDING, reward ships on approval), rejection of duplicate URLs, X-post author verification rules, and that the API takes links only, never uploads. Minor gaps remain on editability or what happens to a rejected submission.

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?

Dense but front-loaded: the core submission rule comes first, then the action-campaign exception, then status guidance. The em-dash-heavy parentheticals are verbose, though nearly every clause carries operational information.

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 mutating, six-parameter tool with no output schema, the description covers the outcome state, duplicate handling, and the action-campaign prerequisite chain, which is what an agent needs to call it once. It leaves out whether submissions can be retried or amended after rejection, which matters for a write operation.

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?

With schema coverage at 83% the schema already carries most parameter text, but the description adds non-obvious semantics: that the proof parameters are alternatives rather than cumulative, that task_id applies only to action campaigns and requires a prior claim, and how direct image links versus video links are rendered to the reviewer.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Submit the user's work for a campaign') and enumerates the three accepted proof forms, so the agent knows exactly what the tool accepts. It stops short of distinguishing itself from the similarly named sibling submit_participation, leaving that overlap to inference.

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?

Explicit routing for each case: 'any one is enough' among proof_url/media_url/description, and a separate branch for action campaigns where task_id is required with the note that an exclusive task 'must be claimed first (claim_task)'. It also names follow-up (get_my_submissions) and the source of screenshot_url (upload_proof_screenshot).

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.