Create a version

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

Annotations indicate non-idempotent, non-read-only, open-world behavior, and the description adds crucial context: versions are immutable, every call creates a NEW version, version numbers only grow, and creating a version does not change what runs anywhere. This goes well beyond the structured annotations.

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 dense sentences, front-loaded with the core action and return value, followed by essential warnings and deployment guidance. Every sentence earns its place without wasted words.

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?

With no output schema, the description appropriately enumerates the return fields. It also covers immutability, non-idempotency, retry guidance, and the follow-up deployment action, leaving no significant gap for an agent to misuse the tool.

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 parameters script_id and description are already fully documented. The description's mention of the return fields relates to output rather than parameter meaning, so it adds no additional parameter semantics.

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 states a specific verb and resource: 'Snapshots the project's current HEAD content as a new immutable version and returns it.' It also clarifies that versions cannot be edited or deleted, clearly distinguishing this from read-only sibling tools like list_versions or get_version.

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 tells the agent not to re-send after an ambiguous failure without checking list_versions first, and explains that shipping the version requires manage_deployments. This gives concrete when-to-use, when-not-to-use, and alternative-tool guidance.

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