download-codeUse this when the user wants the source code of their WebTwizz site as a zip file, for example to host it elsewhere or open it in an editor. Returns a download link the user can open for the next 30 minutes.
| Name | Required | Description | Default |
|---|---|---|---|
| site_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| site_id | Yes | ||
| download_url | Yes | ||
| expires_in_minutes | Yes |
Changes observed during successful MCP inspections.
Output schema / properties / expires_in_minutesAdded value: +{
+ "type": "integer"
+}Output schema / requiredPrevious value: -[
- "site_id",
- "download_url"
-]New value: +[
+ "site_id",
+ "download_url",
+ "expires_in_minutes"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds genuinely non-obvious behavior beyond that: the result is a download link rather than the archive itself, and the link expires after 30 minutes — an operational constraint an agent cannot infer from structured fields.
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, zero waste, and the triggering condition is front-loaded before the return-value detail. Nothing is repeated from annotations or the schema.
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?
An output schema exists, so the description need not detail the response shape, yet it still flags the link and its lifetime. The only shortfall is the missing identification of site_id, which is the single input an agent must supply.
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 0% and the description never mentions site_id, what form it takes, or how to obtain it (presumably from list-sites/get-site). With only one required parameter this is a modest gap, but the description does nothing to compensate for the undocumented schema.
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 verb and resource: delivering the source code of the user's WebTwizz site as a zip file. That is concrete enough to separate it from siblings like get-site, show-preview, or publish-site, though it never names those siblings explicitly.
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?
"Use this when the user wants the source code... for example to host it elsewhere or open it in an editor" gives a clear triggering condition with two concrete example intents. It stops short of exclusions (e.g., use get-site for metadata, use list-versions for rolling back), so it is not a full when/when-not rubric.
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.