Create a new prompt version as an append-only entry without changing the active prompt. Returns an error if the version already exists.
Create a new prompt version (append-only). Does NOT modify current.txt.
Fails if the version already exists.
Updates versions.json without changing its current pointer.
| Name | Required | Description | Default |
|---|---|---|---|
| note | No | ||
| content | Yes | ||
| version | Yes | ||
| agent_id | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden and does substantial work: it discloses append-only semantics, non-modification of current.txt, failure on duplicate versions, and that versions.json is updated without changing its current pointer. It omits success return behavior and auth requirements, so a 5 is not warranted.
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?
The description is compact and front-loaded: the main action and scope appear in the first sentence, followed by two crisp bullet points that capture the key constraints. Every sentence earns its place with no filler or redundancy.
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?
Core behavior and the duplicate-version failure mode are well covered, but with no output schema and no parameter descriptions, an agent still lacks information about what a successful call returns and exactly how to supply the four arguments. The 0% schema coverage leaves necessary invocation details unresolved.
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 does not compensate. None of agent_id, version, content, or note are explained in terms of format, purpose, or constraints; the only implicit hint is that 'version' refers to the prompt version being created, while agent_id and content are left entirely to inference.
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: 'Create a new prompt version (append-only)'. It also distinguishes the tool from read/update siblings by explicitly stating it does not modify current.txt and keeps versions.json's current pointer unchanged, so an agent can tell it apart from prompt-reading tools.
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 is clear this tool is for the append-only creation of a version, and the 'Does NOT modify current.txt' statement is an explicit when-not condition. It does not name alternative sibling tools for updating or reading the current version, which keeps it from a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.