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

Annotations already state readOnlyHint=false and destructiveHint=true, but the description goes far beyond that: it discloses asynchronous execution, skipping of still-generating articles, the Out of Sync side effect on published articles, charging/refund behavior on provider failure, and subscription requirements. These are substantial behavioral disclosures that the annotations alone would not convey.

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 a dense 8-sentence paragraph, but every sentence adds distinct information—async behavior, skip/charge rules, Out of Sync effect, alternative tool, costs, confirm requirement, and website_id. It front-loads the core action and limitation. Slightly long for the information, but well-ordered and free of fluff.

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 complex async batch tool with cost and side effects, the description covers all critical operational context: what happens, when, what to check, what to acknowledge, what prerequisites exist, and how to route to alternatives. The presence of an output schema means return values need no explanation. No important gap is evident.

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 baseline is 3. The description paraphrases the schema's parameter descriptions (confirm, website_id, article_ids, instructions) without adding new meaning. The extra context about credit charging and skipping is behavioral rather than parameter-specific, so there is no significant added semantic value beyond what the schema already provides.

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 opens with a specific verb-resource pair: 'Queues an AI rewrite of up to 50 articles with the same instructions.' It also differentiates from the sibling tool edit_article_with_ai by explicitly pointing to it for single-article or translation use, so an agent can immediately distinguish batch vs. single editing.

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?

Provides explicit when-to-use and when-not-to-use guidance: 'Use edit_article_with_ai for a single article or a translation.' It also covers prerequisites (active subscription/free trial), the confirm flag requirement, the website_id condition, and async behavior with a pointer to check results via get_article. Nothing is left to inference.

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