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

Beyond the destructiveHint=true and readOnlyHint=false annotations, the description discloses the exact write-safety contract: the preview call does not write, delete, cancel, or send, and the confirm_token is single-use with a 5-minute expiry. It also explicitly disables a plausible wrong control (the ignored confirm boolean). This is a genuinely informative behavioral disclosure.

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 front-loaded with the purpose and then the two-step protocol, and nearly every sentence carries actionable information. It is dense and slightly repetitive around the preview/write distinction, but nothing is wasted.

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?

There is no output schema, and the description covers the shape of the first (preview) response, but not what the second, actual write call returns. For a 2-parameter destructive tool this is close to complete, with that one gap.

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%, so the description must carry the load for the two parameters. It explains confirm_token in detail (when to omit it, what it returns, that it is single-use and short-lived), though movement_id is never explicitly described beyond being required.

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 opening sentence states a specific verb and resource ("Post a stock movement draft so inventory changes"), which is clear enough to act on. It doesn't explicitly name the sibling it differs from (e.g., cancel_stock_movement or create_stock_movement), so sibling differentiation is left implicit.

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 clearly explains the two-call protocol: the first call without confirm_token is a dry-run that returns confirmation_required, and the second call repeats the arguments plus the token to perform the write. It also states the token expires in 5 minutes and works once, and that a confirm boolean is ignored, which pre-empts a common misuse. What's missing is guidance on the surrounding lifecycle (e.g., when to cancel a draft instead).

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