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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint. The description adds value by detailing the output structure (fraud probability score, suspicious IP list, pattern analysis) and input requirements (affiliate network, date range). It is consistent with annotations and does not contradict them.

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 three sentences plus a keywords tag, each serving a purpose: purpose, audience/context, inputs/outputs. It is efficient and front-loaded with the core action. However, the keywords tag is redundant and could be omitted for even greater conciseness.

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?

Given the tool has 4 parameters, nested objects, and an output schema (as per context signals), the description adequately covers purpose, inputs, and outputs. It mentions the data source (Common Crawl) and target audience. It does not discuss edge cases or failure modes, but this is acceptable given the read-only, idempotent nature.

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 75%, and the input schema already documents all parameters (affiliate_network, date_range, threshold, async). The description merely restates that inputs are 'affiliate network name and date range', adding no new meaning beyond the schema for these or the other parameters. Baseline of 3 is appropriate.

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 uses a specific verb ('Analyzes') and resource ('affiliate clickstream data from Common Crawl') and clearly states the goal ('flag potential fraud patterns'). It lists example fraud types (duplicate IPs, rapid clicks, device spoofing), distinguishing it from generic fraud detectors. The target audience (CMOs) and business value (prevent budget waste) are also provided.

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 description implies usage context ('Designed for CMOs to validate affiliate traffic quality') but does not explicitly state when not to use the tool or compare it to sibling tools like 'fraud_detector' or 'web_search_multilang'. It lacks explicit exclusions or alternative recommendations.

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