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

The description asserts 'READ-ONLY — it does not block anything', while annotations declare readOnlyHint=false and destructiveHint=true. That is a direct conflict on both the read/write and destructive axes, which can mislead an agent about side effects. The rich detail about scoring reasons and prerequisites cannot offset a contradiction on the safety profile.

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?

Front-loads the core scan purpose and the read-only claim before the lookup mode, with no filler sentences. It is dense but long; the final sentence about form contents not being captured is useful, though the block is heavier than a strict 'every sentence earns its place' bar.

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 structure need not be restated, yet the description still summarizes what is returned (scored IPs, per-IP reasons, click records with time/GCLID/IP/user-agent/referrer/landing page). Prerequisite and workflow coverage are good; the gaps are the unspecified parameters (days, block_threshold, customer_id) and the annotation conflict.

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 burden and does explain actual usage for gclid (from a form lead or CRM), ip, at (Europe/Istanbul, 'YYYY-MM-DD HH:MM', with ±window_minutes), and window_minutes. However days, block_threshold, and customer_id are never explained, leaving three of seven parameters undefined anywhere.

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?

States a specific verb and resource with scope: scans captured ad-click traffic for click fraud/invalid traffic and returns scored suspicious IPs. It also explicitly separates the click-lookup mode and names the sibling tools (block_ip_addresses, fraud_setup) it relates to, so an agent can tell it apart from other fraud/blocking tools.

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?

Gives prerequisites (tag must be installed first via fraud_setup), the downstream workflow (feed recommended_block_ips to block_ip_addresses, which is approval-gated), and the trigger conditions for the lookup mode (matching a fake lead to its ad click via gclid/ip/at). This is explicit routing rather than implied usage.

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