suppression_checkBefore sending: which of these addresses are on your unsubscribe list (unsubscribed, bounced, complained or added by you). Skip every one with suppressed true. Changes nothing.
| Name | Required | Description | Default |
|---|---|---|---|
| emails | Yes | Plain addresses, up to 1000. | |
| instance_id | Yes | Utility instance id from buy or list_utilities. | |
| passport_token | No | Your amp_ token, only if you have no app sign-in and cannot send a header. |
Changes observed during successful MCP inspections.
Input schema / examplesAdded value: +[
+ {
+ "emails": [
+ "reader@example.com",
+ "team@example.org"
+ ],
+ "instance_id": "sup_exampleexampleexample2"
+ }
+]Input schema / properties / passport_token / descriptionPrevious value: -"Your amp_ token, only if your app has no sign-in and cannot send it as an Authorization header."New value: +"Your amp_ token, only if you have no app sign-in and cannot send a header."Input schema / $schemaRemoved value: -"https://json-schema.org/draft/2020-12/schema"Input schema / properties / passport_token / descriptionPrevious value: -"Your amp_ token, only if your client cannot send it as an Authorization header; leave it out when your MCP app signed in."New value: +"Your amp_ token, only if your app has no sign-in and cannot send it as an Authorization header."Input schema / properties / passport_token / maxLengthAdded value: +200Input schema / properties / passport_token / patternRemoved value: -"^amp_(?:s_)?[A-Za-z0-9_-]{43}$"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so 'Changes nothing' is largely reinforcement. The real added value is disclosing the result field name ('suppressed true'), which matters because there is no output schema.
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?
Two short clauses with the precondition front-loaded and zero filler. Every phrase carries either scope, the decision rule, or the safety statement.
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?
With no output schema, the description usefully names the field to branch on. It omits any note on partial results or what a non-suppressed entry looks like, which would fully close the loop for a batch check.
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 100%, so emails, instance_id and passport_token are already documented. The description adds no format, batching or limit guidance beyond what the schema covers, so baseline 3 applies.
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?
States a specific check against a named resource ('your unsubscribe list') and enumerates the categories covered (unsubscribed, bounced, complained, added by you), which distinguishes it from suppression_add/remove/export. It stops short of explicitly naming a sibling to contrast with.
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?
'Before sending:' anchors the tool to a clear moment in the workflow, and 'Skip every one with suppressed true' tells the agent what to do with the result. No explicit when-not or named alternative is given, but the usage context is unambiguous.
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.