Make one version of an app live by its number. This is how a version staged with publish false goes on the link, and how an app is rolled back: name an older number and that version is what the link serves again. Nothing is rebuilt, the pointer moves.
| Name | Required | Description | Default |
|---|---|---|---|
| app_id | Yes | The app id, as returned by search_apps or create_app. Starts with app_. | |
| number | Yes | The version number to make live. |
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?
Beyond the idempotentHint annotation, the description adds meaningful behavior: 'Nothing is rebuilt, the pointer moves.' This tells the agent the operation is a lightweight live-managing action rather than a build or deploy step, and clarifies the rollback effect. It doesn't cover auth or error cases, but those are not central here.
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?
Three short sentences with no filler. The main action is front-loaded, the intended use cases follow, and the behavioral caveat is last. Every sentence earns its place.
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?
For a simple two-parameter tool with fully described parameters, the description and schema together give the agent enough to invoke it correctly: what it does, when to use it, and what effect it has. No output schema is present, but the effect ('pointer moves') is sufficient context for selection and invocation.
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 the baseline is 3. The description reinforces that number is a version number via 'by its number' and 'name an older number,' but adds no new format, source, or units beyond what the schema already documents.
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 a specific verb and resource: 'Make one version of an app live by its number.' It clearly distinguishes this tool from siblings like list_app_versions, read_app_version, and update_app by framing it as the pointer-moving/live-switching operation.
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?
It explicitly names two use cases: publishing a version staged with publish false, and rolling back by selecting an older version. It doesn't name sibling alternatives or exclusions, but the conditions for choosing this tool over read/list/update tools are still evident.
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.
Most tools target clearly distinct actions and resources, such as app CRUD, versioning, sharing, secrets, and folder operations. A few adjacent tools like read_app, read_app_file, and read_app_version, or update_app and publish_app_version, require careful reading, but their descriptions are explicit enough to prevent serious confusion.
The set mostly uses a verb_noun pattern, with names like create_app, list_secrets, set_app_access, and trash_app. However, Unix-style commands like ls, mkdir, mv, tree, and whoami, plus mixed verbs such as get, read, list, remove, and revoke, break any single consistent convention.
24 tools is on the heavy end of the 16-25 range, and while the platform covers apps, versions, folders, sharing, secrets, logs, and databases, the count feels somewhat large. Each tool has a defined role, but several could potentially be consolidated without losing clarity.
The surface covers the main lifecycle well: creating, reading, updating, versioning, sharing, securing, and organizing apps, plus secrets and database queries. Notable gaps are the lack of a permanent delete or restore tool for trashed apps, and the stated absence of captured function logs, but these are workable limitations rather than dead ends.
