XP Tickets

Submit Seller Leads

submit_seller_leads

Submit what you read for one listening job. Call once per assignment, even with no posts.

Returns inserted_count, duplicate_count (already captured, first finder keeps credit) and rejected [{index, reason}] -- e.g. stale_post (older than 72h), raw_text_too_short, post_url_not_canonical, platform_mismatch. Do not resubmit rejected posts unchanged.

Input Schema

Name	Required	Description
`leads`	No	Up to 50 posts. Each: post_url (canonical post link), author_username, posted_at (ISO-8601), raw_text (the post copied word for word, 20+ chars), intent_type (sell\|buy\|trade\|noise), item_category (tickets\|sublet\|merch\|other), and when known: matched_event_id (from search_events), match_confidence (0-1), performer, venue, city_state, event_date (YYYY-MM-DD), quantity, section, row, seats, asking_price_dollars, price_basis (per_ticket\|total), author_profile_url.
`assignment_id`	Yes	The assignment_id from get_listening_assignment.
`could_not_read`	No	True when you could not open the source (login wall, blocked site, gone). Send no leads. The job is not counted as a scan, and this agent is not given that source again for an hour.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedOct 29, 2026

addedInput schema / properties / could_not_read

Added value: +{
+  "default": false,
+  "description": "True when you could not open the source (login wall, blocked site, gone). Send no leads. The job is not counted as a scan, and this agent is not given that source again for an hour.",
+  "type": "boolean"
+}

addedInput schema / properties / leads / anyOf

Added value: +[
+  {
+    "items": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "type": "array"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / leads / default
```
Added value: +null
```

removedInput schema / properties / leads / items

Removed value: -{
-  "additionalProperties": true,
-  "type": "object"
-}

removedInput schema / properties / leads / type
```
Removed value: -"array"
```

changedInput schema / required

Previous value: -[
-  "assignment_id",
-  "leads"
-]New value: +[
+  "assignment_id"
+]

AddedOct 29, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations only declare it is a non-destructive write; the description adds genuinely new behavior: dedup with first-finder credit, rejection with index/reason, a 72h staleness window, and canonical URL requirements. Some of this overlaps the output schema's rejected array, but the credit and resubmission semantics are not in structured fields.

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?

Three short sentences with the core instruction front-loaded, then return shape, then the one prohibition. No filler; every clause carries a rule an agent must obey.

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?

Output schema exists so return values need not be spelled out, and the description still summarizes them usefully. What is missing is the failure/retry path for assignment_id mismatch or oversized lead batches, though both are partially 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% and the schema already documents leads, assignment_id, and could_not_read in detail, so the baseline is 3. The description adds only the implicit 'empty leads is valid' case and does not clarify field-level semantics beyond the schema.

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 ('Submit what you read for one listening job') and names the counterpart tool by implication via assignment_id, distinguishing it from read-side siblings like get_listening_assignment. An agent immediately knows this is the write-back step of the listening workflow.

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?

Explicitly says 'Call once per assignment, even with no posts' and 'Do not resubmit rejected posts unchanged', which are real usage rules an agent would otherwise get wrong. It does not explicitly contrast with submit_discovered_sources or say what to do between assignments, so it falls short of full when/when-not guidance.

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

All XP Tickets 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?