supportpages_recommend_articles

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

Annotations already declare destructiveHint=true, openWorldHint=true, and readOnlyHint=false, so the safety profile is largely covered. The description usefully adds that the call returns a durable (async, retrievable) operation and that output is gated behind human review. It does not explain, despite destructiveHint=true, what state is modified or what the durability implies for retries/recovery.

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 short sentences, front-loaded with the core action and immediately followed by the review-gate constraint. No filler, though the final prohibition sentence is a slight grab-bag of three separate rules.

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?

An output schema exists, so return-value detail is not required. The description does cover the async/durable operation model and the pending-review semantics, which an agent needs. It remains incomplete on the three undocumented parameters and on how this tool relates to its recommendation-oriented siblings.

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 only 25%: only request_id is documented in the schema, and it carries a solid description there. The description says nothing about workspace, open_when_ready, or prefer_background, so three of four parameters have no meaning anywhere. With low coverage the description is expected to compensate, and it does not.

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 gives a specific verb and resource ('Run hosted documentation analysis and return a durable operation'), and 'Suggestions remain pending for review' implies the recommend-articles behavior. However, it never states outright that it produces article recommendations, and it does not distinguish itself from close siblings like supportpages_suggest_sections, supportpages_find_article_gaps, or supportpages_list_recommendations.

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 prohibitions ('Never analyse locally, accept suggestions automatically or generate articles implicitly') are genuine usage constraints that shape agent behavior. What is missing is positive routing: no statement of when to pick this over find_article_gaps, suggest_sections, or list_recommendations, and no prerequisites or ordering relative to review_recommendations.

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