contactSend free support or appeals, or paid private item messages with request_id and max_fee. Reads are free; messages never authorize spending. See auction://reference.
| Name | Required | Description | Default |
|---|---|---|---|
| to | No | ||
| text | No | ||
| human | No | ||
| action | Yes | ||
| max_fee | No | ||
| message | No | ||
| entry_id | No | ||
| request_id | Yes | ||
| decision_id | No | ||
| conversation_id | No |
Changes observed during successful MCP inspections.
Input schema / $defs / conversation_idRemoved value: -{
- "format": "uuid",
- "pattern": "^([\\da-fA-F]{8}-[\\da-fA-F]{4}-[1-8][\\da-fA-F]{3}-[89abAB][\\da-fA-F]{3}-[\\da-fA-F]{12}|0{8}-0{4}-0{4}-0{4}-0{12}|f{8}-f{4}-f{4}-f{4}-f{12})$",
- "type": "string"
-}Input schema / $defs / entry_idAdded value: +{
+ "format": "uuid",
+ "pattern": "^([\\da-fA-F]{8}-[\\da-fA-F]{4}-[1-8][\\da-fA-F]{3}-[89abAB][\\da-fA-F]{3}-[\\da-fA-F]{12}|0{8}-0{4}-0{4}-0{4}-0{12}|f{8}-f{4}-f{4}-f{4}-f{12})$",
+ "type": "string"
+}Input schema / oneOfPrevious value: -[
- {
- "properties": {
- "action": {
- "enum": [
- "message"
- ]
- },
- "decision_id": false,
- "entry_id": false,
- "request_id": {
- "$ref": "#/$defs/conversation_id"
- },
- "text": false
- },
- "required": [
- "message"
- ]
- },
- {
- "properties": {
- "action": {
- "enum": [
- "appeal"
- ]
- },
- "conversation_id": false,
- "entry_id": false,
- "human": false,
- "message": false,
- "request_id": {
- "$ref": "#/$defs/conversation_id"
- },
- "to": false
- },
- "required": [
- "decision_id",
- "text"
- ]
- },
- {
- "properties": {
- "action": {
- "enum": [
- "item_message"
- ]
- },
- "decision_id": false,
- "human": false,
- "request_id": {
- "$ref": "#/$defs/conversation_id"
- },
- "text": false,
- "to": false
- },
- "required": [
- "message"
- ]
- }
-]New value: +[
+ {
+ "properties": {
+ "action": {
+ "enum": [
+ "message"
+ ]
+ },
+ "decision_id": false,
+ "entry_id": false,
+ "request_id": {
+ "$ref": "#/$defs/entry_id"
+ },
+ "text": false
+ },
+ "required": [
+ "message"
+ ]
+ },
+ {
+ "properties": {
+ "action": {
+ "enum": [
+ "appeal"
+ ]
+ },
+ "request_id": {
+ "$ref": "#/$defs/entry_id"
+ }
+ },
+ "propertyNames": {
+ "enum": [
+ "decision_id",
+ "request_id",
+ "text",
+ "action",
+ "max_fee"
+ ]
+ },
+ "required": [
+ "decision_id",
+ "text"
+ ]
+ },
+ {
+ "properties": {
+ "action": {
+ "enum": [
+ "item_message"
+ ]
+ },
+ "decision_id": false,
+ "human": false,
+ "request_id": {
+ "$ref": "#/$defs/entry_id"
+ },
+ "text": false,
+ "to": false
+ },
+ "required": [
+ "message"
+ ]
+ }
+]Input schema / properties / conversation_id / $refPrevious value: -"#/$defs/conversation_id"New value: +"#/$defs/entry_id"Input schema / properties / decision_id / $refPrevious value: -"#/$defs/conversation_id"New value: +"#/$defs/entry_id"Input schema / properties / entry_id / $refPrevious value: -"#/$defs/conversation_id"New value: +"#/$defs/entry_id"Input schema / properties / funding_accountsRemoved value: -{
- "additionalProperties": false,
- "properties": {
- "grant_account_id": {
- "format": "uuid",
- "type": "string"
- },
- "normal_account_id": {
- "format": "uuid",
- "type": "string"
- }
- },
- "type": "object"
-}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare it is not read-only, is open-world, idempotent, and non-destructive. The description adds useful behavioral context beyond that: support/appeals are free, item messages are paid, and messages never authorize spending. It does not detail external side effects or rate limits, but the cost/spending clarification is meaningful.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded and compact: it states the main operation, the free/paid distinction, and a key safety constraint. The reference pointer is brief and no sentence is wasted.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
This is a complex tool with a oneOf schema, 10 parameters, and no output schema. The description gives only a high-level summary and points to auction://reference, but it does not explain variant selection, required fields per action, or most parameter meanings, leaving too much to external documentation or inference.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% across 10 parameters, so the description must carry parameter meaning. It mentions request_id and max_fee and loosely maps to action modes, but leaves many parameters undocumented, including to, text, human, message, entry_id, decision_id, conversation_id, and the action enum values.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb and resource set: sending free support/appeals and paid private item messages. It distinguishes the free and paid modes and mentions request_id/max_fee, though it does not explicitly differentiate this tool from siblings like feedback or account.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use each mode: free support/appeals versus paid private item messages. However, it gives no explicit guidance on when to choose this tool over alternatives such as feedback or account, nor does it state exclusions or prerequisites beyond max_fee for paid messages.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.