sendgrid_add_or_update_contactsUPSERTS marketing contacts (creates new ones, updates existing ones by email) and optionally adds them to lists. This is an ASYNC job — returns { job_id } you can poll. SendGrid: PUT /v3/marketing/contacts.
| Name | Required | Description | Default |
|---|---|---|---|
| contacts | Yes | Contacts to add or update (each needs an `email`; custom fields pass through). | |
| list_ids | No | List ids to add these contacts to. |
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?
The description adds significant behavioral detail beyond the destructiveHint annotation. It discloses that the operation is asynchronous, returns a job_id for polling, and that existing contacts are updated by email. It also references the underlying API endpoint (PUT /v3/marketing/contacts), giving the agent a fuller understanding of side effects and execution flow.
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 compact and efficiently structured: the verb comes first, followed by clarifying details, async behavior, return format, and the API endpoint. Every sentence adds value, and there is no redundant or filler content.
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?
Although the tool has no output schema, the description compensates by explicitly stating the return format ({ job_id } for polling). For a tool with two parameters and a nested contact object, the description covers purpose, behavior, and return value. It is complete enough for an agent to invoke and interpret the result.
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 already provides thorough descriptions for both parameters (contacts and list_ids), covering 100% of them. The description adds minimal parameter-specific detail beyond 'optionally adds them to lists,' which mirrors the schema. Given the high schema coverage, a baseline score 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 opens with the specific verb 'UPSERTS' and clearly identifies the resource ('marketing contacts'), then elaborates with 'creates new ones, updates existing ones by email.' It distinguishes the tool from siblings like sendgrid_send_mail or sendgrid_search_contacts_by_email by focusing on contact record creation/update, making its purpose unambiguous.
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 provides clear context: this is the tool for adding or updating marketing contacts and optionally associating them with lists. It also notes the async nature, which guides agents to expect a job_id rather than immediate results. While it does not explicitly mention when not to use it or name alternatives, the context makes the intended use obvious.
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.
Each tool targets a distinct resource/action: send mail, manage contacts (upsert/count/search), templates (get/list), suppression lists (bounces/unsubscribes), marketing lists, stats, and health check. No overlaps or ambiguous boundaries.
All tools follow a consistent 'sendgrid_' prefix with a verb_noun pattern (e.g., get_template, list_bounces, send_mail). The only minor deviation is 'ping' for health check, but it's a conventional verb-only name and doesn't break the overall consistency.
11 tools is well-scoped for a SendGrid server, covering sending, contacts, templates, suppression, stats, and health. Each tool has a clear purpose and none feel redundant.
Core email sending, contact management, and read operations for templates/suppression are covered. However, there are no write operations for templates (create/update/delete) or suppression list management (remove), which are minor gaps that agents can work around by using the existing tools.