x_action_prepare

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

Beyond annotations (readOnlyHint=false, openWorldHint=true), the description adds meaningful behavioral context: it does not submit, requires the intended account handle, returns an exact preview, and produces an expiring single-use action ID. It also clarifies target type semantics by action kind. No contradiction with 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 sentences with no filler. The verb and scope are front-loaded, followed by the key non-submission trait, then the requirements and return value. Each 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?

Given the lack of output schema and sparse annotations, the description does a good job covering purpose, non-submission behavior, return value, account requirement, and target semantics. However, it omits how the returned action ID is consumed (e.g., with x_action_execute) and does not clarify whether text/target are required for specific actions, which could leave an agent uncertain on edge cases.

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?

With 0% schema description coverage, the description must compensate. It explains expectedAccount ('Requires the intended account handle'), target ('Post targets are X post URLs; follow targets are handles'), and the action enum by listing supported verbs. Text is only vaguely implied as content for post/reply, and target requirement is not fully mapped per action, but it covers most parameter meaning.

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 uses a clear verb ('Prepare') plus a specific resource ('a specific text post/reply, like/unlike, bookmark/unbookmark, repost/unrepost, or follow/unfollow'). It explicitly distinguishes this from submission ('Does not submit') and from sibling execute/cancel/receipt tools by describing the preview and action ID.

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 clearly signals the tool is a non-submitting preparation step by stating 'Does not submit' and 'returns exact preview and an expiring single-use action ID.' This implies it should be used before x_action_execute, but it does not explicitly name the alternative or state when not to use it. The context is clear, but exclusions are not explicit.

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