List outbound messages (sent and scheduled) of one mail account; received mail is not included.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | ||
| size | No | Default 20 | |
| view | No | summary | |
| status | No | Default: all | |
| date_to | No | Unix seconds | |
| date_from | No | Unix seconds; filters on scheduled/sent time | |
| from_account_id | Yes | Mail account id from hires_list_company_mail_accounts or hires_list_user_mail_accounts |
Changes observed during successful MCP inspections.
Input schema / $schemaRemoved value: -"http://json-schema.org/draft-07/schema#"Input schema / additionalPropertiesRemoved value: -falseInput schema / properties / date_from / descriptionPrevious value: -"Start of period (unix timestamp, seconds). Filters on scheduled/sent time."New value: +"Unix seconds; filters on scheduled/sent time"Input schema / properties / date_to / descriptionPrevious value: -"End of period (unix timestamp, seconds). Filters on scheduled/sent time."New value: +"Unix seconds"Input schema / properties / from_account_id / descriptionPrevious value: -"ID of the mail account (from `GET /companies/mail-accounts` or `GET /users/{user_id}/mail-accounts`)."New value: +"Mail account id from hires_list_company_mail_accounts or hires_list_user_mail_accounts"Input schema / properties / page / descriptionRemoved value: -"Page number (1-based). Default: 1."Input schema / properties / size / descriptionPrevious value: -"Number of items per page (1-100). Default: 20."New value: +"Default 20"Input schema / properties / status / descriptionPrevious value: -"Filter by message status: `scheduled` (pending send), `sent` (delivered), `all` (both). Default: `all`."New value: +"Default: all"Input schema / properties / view / descriptionRemoved value: -"Response shape. Default `summary` excludes the HTML body and attachments metadata — recommended for list operations. Use `full` only when message body content is needed."Input schema / properties / viewAdded value: +{
+ "default": "summary",
+ "description": "Response shape. Default `summary` excludes the HTML body and attachments metadata — recommended for list operations. Use `full` only when message body content is needed.",
+ "enum": [
+ "summary",
+ "full"
+ ],
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the agent knows it's a safe read operation. The description adds that received mail is not included, which is useful behavioral context. However, it doesn't mention pagination limits (size max 100) or the view modes, which are in the schema but not behavioral traits beyond annotations.
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 a single concise sentence that front-loads the key purpose and exclusion. It captures the essential scope without fluff, earning a high score for efficiency.
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?
Given the tool is a read-only list with a clear scope and schema covering most parameters, the description is adequate but not exhaustive. It doesn't explain the meaning of the status filter or the view difference, but those are inferable from the enum names. Overall, it meets the minimum viable standard for calling the tool correctly.
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 71%, so most parameters have descriptions from the schema. The description adds little beyond the schema—it confirms the account filter. Some parameters like date_to and date_from lack full semantic explanation, but the schema provides enough for basic use. The description doesn't compensate for the gaps.
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 ('List') and resource ('outbound messages'), and explicitly excludes received mail, which helps distinguish from a generic message list. It doesn't name sibling alternatives, but the scope is clear enough for an agent to infer its purpose.
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 this is for listing messages for a specific account (requires from_account_id) and filters to outbound onlyvoice. It doesn't explicitly say when to use this over sibling tools like hires_list_candidate_messages or hires_send_candidate_message, but the exclusion of received mail provides some context. No explicit alternatives or when-not-to-use guidance is present.
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.