mark_messages_readRetry-safely mark messages read or unread and return a durable per-item receipt. Reuse the exact idempotency key after timeouts. API: PATCH /api/emails/{address}/messages/read.
| Name | Required | Description | Default |
|---|---|---|---|
| read | Yes | true = mark as read, false = mark as unread | |
| slug | Yes | Mailbox slug | |
| domain | Yes | Mailbox domain | |
| message_ids | Yes | IDs of messages to mark | |
| idempotency_key | Yes | Caller-stable key for this exact logical batch |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / properties / idempotency_keyAdded value: +{
+ "description": "Caller-stable key for this exact logical batch",
+ "maxLength": 200,
+ "minLength": 8,
+ "type": "string"
+}Input schema / requiredPrevious value: -[
- "domain",
- "slug",
- "message_ids",
- "read"
-]New value: +[
+ "domain",
+ "slug",
+ "message_ids",
+ "read",
+ "idempotency_key"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses retry safety, a durable per-item receipt, and the API endpoint, which is helpful. However, it omits permission requirements, error behavior, and how partial failures are handled, making it moderate transparency.
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 three short sentences, front-loaded with the primary purpose, then a critical usage tip and the API reference. Every sentence earns its place with no redundancy.
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?
Without an output schema or annotations, the description provides a high-level 'durable per-item receipt' but lacks the exact return structure and edge-case behavior (e.g., invalid message IDs, partial failures). It is sufficient for basic understanding but not fully complete.
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?
The schema provides 100% coverage of all five parameters, so the baseline is 3. The description adds value by explaining the idempotency key reuse after timeouts, but it does not elaborate on other parameters beyond the schema, which is acceptable.
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 clearly states the tool marks messages read or unread, with a specific API endpoint and retry-safe behavior. However, it does not explicitly differentiate from sibling tools like update_email_messages, so it stops short of a 5.
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?
Provides clear context that this tool is for idempotent read/unread marking and explicitly instructs to reuse the idempotency key after timeouts. It does not mention alternatives or exclusions, so it earns a 4 rather than a 5.
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.
While most tools have distinct purposes, several clusters overlap significantly (e.g., check_email, check_email_deliverability, get_email_deliverability, get_domain_email_status; buy_domain, buy_aftermarket, acquire_domain). The descriptions are detailed and help differentiate, but the sheer number of tools makes it challenging for an agent to select the correct one without careful reading.
The dominant pattern is verb_noun with underscores (e.g., create_mailbox, list_domains), but there are notable inconsistencies: destructive actions mix delete/remove/cancel/revoke/unsell, and a few names deviate entirely (search, dns_check, domain_status). The pattern is recognizable but not uniformly applied.
With 122 tools, this vastly exceeds the 50+ threshold for extreme mismatch. Even for a comprehensive domain and email platform, the tool count is overwhelming and will likely hinder agent performance through excessive choice and context bloat.
The server covers a wide range of domains, DNS, email, marketplace, negotiations, transfers, webhooks, tokens, and billing. Minor gaps exist, such as no update operation for mail rules, no direct domain deletion, and limited mailbox configuration beyond forwarding and credentials, but most lifecycle workflows are supported.