Create a message stream for transactional or broadcast email. Set a custom permalink or let the API derive one from the name.
Create a message stream. Set permalink explicitly when you need to know it up front; the API derives one from the name otherwise.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Display name | |
| permalink | No | URL-safe identifier used in every later call | |
| stream_type | No | Defaults to transactional |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full behavioral burden. It discloses one genuinely useful trait — the API derives permalink from name when not set — but does not cover other behaviors an agent might need, such as failure on duplicate names, idempotency, or what side effects creation has. Partial but not comprehensive disclosure.
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 sentences with zero filler. The purpose is front-loaded and the conditional permalink guidance earns its place by conveying the tool's key operational nuance.
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?
The tool is simple and all three params are schema-documented at 100% coverage, but there is no output schema and the description doesn't mention what the API returns upon creation (e.g., the created stream with its permalink). Given the permalink guidance implies the identifier matters for later calls, noting the return shape would meaningfully improve completeness.
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 coverage is 100%, so the baseline is 3, but the description adds real meaning beyond the schema: it explains that permalink can be known up front if set explicitly and is otherwise derived, which clarifies the relationship between name and permalink that the schema alone doesn't convey.
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?
'Create a message stream' is a specific verb+resource statement that clearly distinguishes this tool from siblings like update_stream, archive_stream, and list_streams. The scope is unambiguous and an agent can immediately tell what this tool does.
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 gives conditional guidance on when to set permalink explicitly versus letting the API derive it, which is useful within the tool. However, it never addresses when to choose create_stream over related tools like send_to_stream or archive_stream, so sibling routing is left to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.