Sessy — Amazon SES observability

Create source

create_source

Create a new email source (one per app or mail stream) and return the AWS SES wiring details for it: webhook URL for the SNS subscription, suggested configuration set and topic names, and the remaining setup steps. Retention is configured in the web UI.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`name`	Yes	Display name, e.g. the app or mail stream it tracks
`color`	No	Badge color in the web UI; defaults to the least-used color

Output Schema

TableJSON Schema

Name	Required	Description	Default
`setup`	Yes
`source`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 3, 2026

changedOutput schema / properties / setup / properties / aws_region / description

Previous value: -"SES region chosen on the Setup page; null until picked"New value: +"SES region, chosen on the Setup page or inferred from the confirmed SNS topic; null until then"

changedOutput schema / properties / setup / properties / launch_stack_url / description

Previous value: -"CloudFormation quick-create link that provisions everything in the user's AWS account; null until a region is picked"New value: +"CloudFormation quick-create link that provisions everything in the user's AWS account; opens the console's last-used region until aws_region is set"

changedOutput schema / properties / setup / properties / launch_stack_url / type
```
Previous value: -[
-  "string",
-  "null"
-]New value: +"string"
```

Changed3 schema fields changedOct 2, 2026

addedOutput schema / properties / setup / properties / aws_region

Added value: +{
+  "description": "SES region chosen on the Setup page; null until picked",
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / setup / properties / launch_stack_url

Added value: +{
+  "description": "CloudFormation quick-create link that provisions everything in the user's AWS account; null until a region is picked",
+  "type": [
+    "string",
+    "null"
+  ]
+}

changedOutput schema / properties / setup / required

Previous value: -[
-  "webhook_url",
-  "config_set_name",
-  "sns_topic_name",
-  "setup_url",
-  "steps"
-]New value: +[
+  "webhook_url",
+  "config_set_name",
+  "sns_topic_name",
+  "aws_region",
+  "launch_stack_url",
+  "setup_url",
+  "steps"
+]

AddedSep 28, 2026

TDQS

A4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safety profile (not read-only, not idempotent, non-destructive, closed-world). The description adds real value beyond them by disclosing the returned SES wiring payload and that retention is deliberately not settable via the API and must be done in the web UI. It omits auth requirements and duplicate-name behavior, keeping it at 4.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences: the create action and its return payload are front-loaded, and the retention caveat is appended as a short boundary clause. No filler or restatement of the title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description need not enumerate return fields, and the annotations carry the safety profile. It covers scope, the creation cadence, and the retention boundary, but says nothing about behavior on duplicate names or permissions, leaving a small gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%: 'name' and 'color' are both documented in the schema, including the enum values and the least-used-color default. The description adds no parameter-level detail (its only configuration remark, retention, is explicitly not a parameter), so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (create a new email source) and even discloses the return payload (SES wiring details, webhook URL, config set/topic names). It does not explicitly differentiate from siblings such as get_source_setup, which also surfaces setup details, so it falls 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.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The parenthetical 'one per app or mail stream' gives clear context for when a source should be created, and the retention note defines a boundary of API responsibility. There is no explicit when-not guidance or pointer to update_source for existing sources, so it stops short of 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Sessy — Amazon SES observability tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.