UGC Agent

Run UGC Agent

run_ugc_agent

Run a full UGC Agent sourcing/refine/export turn on the web app's search engine. Returns an app_url for table review and CSV export. Small targets finish inside the call and return the creators. A longer search returns status 'running' with list_id, found_so_far and an instruction: wait about 30 seconds and call get_run_status with that list_id instead of calling this tool again. Negations in the goal are honoured; plan limits, stored preferences and cross-run dedupe are applied by the web app for the signed-in user.

Input Schema

Name	Required	Description
`uid`	No	Optional Firebase uid. Must match the URL uid unless local fallback is enabled.
`goal`	Yes	Plain-English sourcing/refine/export request.
`target`	No	Fallback number of new leads to add.
`bearer_token`	No	Optional Firebase ID token. Hosted clients normally authenticate with an API key in the Authorization header or ?uid= in the URL instead.
`seed_handles`	No	Example Instagram handles/URLs for 'find more like these'.
`exclude_niches`	No	Verticals the user ruled OUT ('any niche but photography' -> ['photography']). Negations written in the goal are also honoured automatically.
`conversation_id`	No	Creator-list key for durable state. Reuse a returned list_id for follow-ups; when omitted, MCP uses the active generated list for this tool chain.
`preferences_mode`	No	How to apply preferences for this call: 'stored' uses users/{uid}.agentPreferences, 'override' uses agent_preferences only, and 'none' disables stored filtering for this run.
`agent_preferences`	No	Optional per-call filtering preferences. Use with preferences_mode='override'. For backwards compatibility, passing this without preferences_mode implies override.
`exclude_locations`	No	Markets the user ruled OUT, as ISO country codes ('any country except India' -> ['IN']). Negations written in the goal are also honoured automatically.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 31, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations say readOnlyHint=false, openWorldHint=true, idempotentHint=false, and destructiveHint=false. The description adds substantial context beyond them: synchronous versus asynchronous return shapes, the 30-second polling instruction, negation handling, plan limits, stored preferences, and cross-run dedupe.

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?

The description is compact and front-loaded: it opens with the core action, then covers the two return modes, the async polling instruction, and applied defaults. Every sentence carries operational value.

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?

Given 10 parameters, no output schema, and non-idempotent/open-world annotations, the description supplies the key missing behavioral detail: what the tool returns in fast versus long-running cases and how to continue. Parameter details are already covered by the schema.

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 100%, so the schema already documents all 10 parameters in detail. The description reinforces goal negation handling and stored-preference behavior, but it does not add parameter-level syntax or format details beyond what the schema provides.

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: running a full UGC Agent sourcing/refine/export turn on the web app's search engine. It also distinguishes the tool from get_run_status by explaining when the call finishes synchronously versus when status polling is needed.

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?

Explicitly describes the small-target case, the longer-search case, and the required alternative: call get_run_status with the returned list_id instead of calling run_ugc_agent again. This is exactly the when-to-use/when-to-switch guidance an agent needs.

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

All UGC Agent tools Inspect

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

Need Help?