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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so safety is covered structurally. The description adds one genuinely useful interpretive caveat, 'Co-occurrence, not cause,' warning the agent not to over-read correlations. It still says nothing about aggregation level, time-window behavior, or what a result set looks like.

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 terse fragments with no wasted words, and the data-domain scope is front-loaded ahead of the interpretation caveat. It is arguably over-terse for the amount of undocumented surface, but structurally it is clean.

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?

With no output schema, four undocumented parameters, and a dense sibling set, the description should explain what an 'insight' returns and how to scope dates. Instead it offers only a scope fragment and a caveat, leaving the agent without enough to call the tool correctly or interpret its output.

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 carries the full burden for four parameters (project_id, range, start_date, end_date), including a range enum of 30d/90d/1y. The description adds zero parameter meaning and never even mentions the date window or its relation to the range enum. Baseline does not apply here because coverage is far below 50%.

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 the data domains (AI crawler, referral, citation) and the output shape (patterns), which suggests aggregation rather than the per-page/per-URL focus of siblings like read_ai_traffic_pages and read_ai_traffic_url. However, it contains no verb and never explicitly states it reads a report, so it largely echoes the name/title. Distinguishing it from the ~10 other read_ai_* siblings is left to inference.

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?

No when-to-use guidance, no exclusions, and no mention of alternatives. The crowded read_ai_* sibling set (crawlability, referrals, shelf, traffic_pages, traffic_url) demands routing cues, and none are given. The agent must guess based on the name alone.

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