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

Annotations already carry destructiveHint=true and readOnlyHint=false; the description adds determinism, no AI generation, the complete-permutation requirement for order, and the 409 stale behavior. It could more explicitly warn about overwriting existing question text, but it does not contradict the 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?

Two dense sentences front-load the core action and then add only high-value caveats: read first, stable ids, no AI generation, and stale conflict behavior. There is no filler or repetition of schema details.

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?

For a destructive nested-parameter tool with no output schema, the description covers the core workflow, id semantics, ordering constraint, and concurrency failure. It leaves common top-level fields such as request_id and idempotency_key to the schema, which is reasonable.

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%, but the description compensates for key parameters: order must be a complete permutation of resulting ids, questions are referenced by stable question_N ids, and source_stage acts as a version guard. It doesn't detail text/guidance/followUpQuestions/tags fields, but the schema property names and 'rewrite' wording cover much of that.

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 names a specific verb and resource: 'Replace one draft round's questions by id and/or reorder them with order.' It clearly separates this from add/delete/generate siblings by limiting scope to existing questions and explicitly stating 'deterministic, no AI generation.'

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 gives actionable context: 'Read the draft first: stored questions expose stable question_N ids' and explains when source_stage should be provided and what stale versions do. It does not explicitly name alternatives like add_questions or delete_questions, but the replacement/reorder wording makes the boundary reasonably clear.

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