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

Annotations already declare readOnlyHint=true and openWorldHint=true, yet the description adds substantive behavior: the AI-session attribution rule (channel OR known source), the ~10% gap filed as Referral, the cap of 25 properties for "all", the partial final ISO week, and the caveat that engines[].key_events are sums that exceed sessions. It also warns against over-claiming AI conversion superiority from an aggregate median, which is real interpretive guidance.

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?

It is front-loaded with purpose, then usage, then result interpretation, with zero filler sentences — each claim (attribution rule, ratio choice, key-event caveat, partial week) is actionable. The length is justified by analytical complexity, though the block is dense enough that light trimming of the parenthetical measurement asides would help scanning.

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, yet the description goes further and explains how to read the key fields (ai_to_organic vs ai_share_of_total, pages paired with organic sessions, rates from ai_totals). For a read-only analytics tool with 3 simple params, nothing an agent needs to invoke or interpret it is missing.

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 already 100%, so the baseline is 3; the description still adds meaning beyond the schema for property_id by explaining that "all" returns one summary row per property limited to the first 25 the user can see. The days and page_limit semantics are already fully covered in the schema, so no additional credit is warranted there.

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 opening sentence names a specific resource (traffic from AI assistants), the named engines, the breakdowns (engines, pages), and the comparison against Google organic. This is clearly separable from generic siblings like ga4_traffic_sources or ga4_top_pages because it is scoped to AI-assistant-referred sessions.

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 lists concrete user questions the tool answers ("do AI assistants recommend my site?", "how much traffic does ChatGPT send?", GEO/AEO/LLM visibility) and states an explicit boundary: it measures visits only and cannot see mentions without a click. It also flags the portfolio-comparison mode via property_id="all", so the agent knows both when to reach for it and what it will not cover.

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