Queue one idempotent transactional delivery.
| Name | Required | Description | Default |
|---|---|---|---|
| to | Yes | Recipient email | |
| reply_to | No | Optional reply-to email | |
| domain_id | Yes | Active sending domain ID | |
| variables | Yes | ||
| template_id | Yes | Published template ID | |
| idempotency_key | Yes | Unique logical message key | |
| organization_id | Yes | Active organization ID | |
| template_version | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral disclosure burden. 'Queue' communicates that the send is asynchronous rather than immediate, and 'idempotent' signals safe retries with the same key. It does not disclose what happens on duplicate idempotency keys, failure behavior, or whether a delivery identifier is returned.
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 single sentence is tight, front-loaded, and contains no filler words. It is concise without being redundant, though it is so short that some useful elaboration is sacrificed.
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?
For a tool with 8 parameters, a nested variables object, no annotations, and no output schema, the description is far too sparse. It does not explain return behavior, how variables should be structured, what happens after queueing, or how this relates to the many sibling messaging tools. The description provides a useful seed but is not complete enough for an agent to invoke this tool confidently in complex scenarios.
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 covers 75% of parameters, and the description adds minimal parameter-specific meaning. 'Idempotent' loosely maps to the idempotency_key parameter and 'delivery' to the recipient/template context, but the description does not clarify the nested 'variables' object or 'template_version' semantics. Schema already documents most parameters, so a baseline of 3 is appropriate.
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 uses a specific verb ('Queue') with a resource ('one idempotent transactional delivery'), making the core operation clear. It distinguishes itself from campaign and marketing tools by emphasizing 'transactional' and 'one' delivery, though it does not explicitly mention that this is an email message.
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 word 'transactional' implies this is for single operational messages rather than marketing campaigns, and 'one' suggests it is not a bulk-send tool. However, it does not explicitly state when not to use it or name an alternative sibling tool, leaving some routing decisions to inference.
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.
Most resource CRUD sets are distinct, but the server duplicates entire CRM activity/task tool groups under crm_* and platform_crm_* with identical descriptions, so an agent cannot tell which set to call. Additional overlap exists around identity/context (me, context, platform_context, organizations) and exports (contacts_export vs data_export_create).
Names generally follow commsharbor_<resource>_<action>, but list endpoints are split between plural nouns (audiences, webhooks) and *_list suffixes (crm_activities_list), and some tools use bare nouns or verbs (health, me, context, logout). The mixed conventions are readable but not fully predictable.
141 tools is far beyond a coherent surface for an agent to select from. Even with a broad CRM/email platform scope, the set should be consolidated, namespaced more aggressively, or split into multiple focused servers.
Coverage is broad: campaigns, templates, audiences, CRM objects, imports/exports, auth, billing, domains, webhooks, and suppressions all have lifecycle tools. Gaps like suppression deletion, webhook update, and a non-platform leads group are minor relative to the overall surface, though the duplicate platform sets muddy completeness.