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

Annotations declare readOnlyHint=false and destructiveHint=false, so this is a mutation without data destruction. The description adds useful behavioral details: it explains that the operation uses after/before to position an item, and specifically how to move to the front (target the first field) and to the end (target the last field). It also clarifies that after and before are mutually exclusive by saying 'choose either'. This goes beyond the bare annotations without contradicting them.

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 three sentences long and front-loaded with the core action. Each sentence earns its place: the first states the purpose, the second explains the after/before mechanism, and the third covers the front/end edge cases. It contains no fluff or repetition, making it efficient and easy to scan.

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 tool has an output schema (which covers return values), the description need not explain those. It adequately covers the essential operational details: what to move, how to specify a relative position, and how to achieve first/last placement. It does not mention error conditions like 'code not found' or 'both after and before provided', but the schema's required fields and the explicit 'choose either' mitigate that. Overall, an agent has enough information to call it correctly.

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 coverage is 100%, so each parameter is already described in the schema. The description adds semantic value by explaining the relationship between 'code' (the item to move) and 'after'/'before' (the reference points), and by providing the front/end strategy. It clarifies the meaning of the parameters beyond their individual descriptions, which lifts it above the baseline 3.

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 clearly states the action ('Move an existing item'), the resource types (question, page break, display block), and the mechanism (by code, positioning relative to another field). It distinguishes from sibling tools by focusing on reordering existing items rather than creating or updating content, and it gives concrete examples for moving to the front or end.

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 provides implicit usage guidance by stating the tool moves existing items, which rules out creation scenarios, and explains how to achieve front/end positioning. It does not explicitly mention alternatives like insert_question or delete_question, but the mechanics of after/before and the front/end examples give the agent enough context to decide when this tool is appropriate. A bit more explicit exclusion of creating new items would push it to 5.

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