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

Annotations already declare readOnlyHint=true and idempotentHint=true, but the description adds critical behavioral context: it mentions that results include a thread_id, and the agent MUST include it unchanged on every subsequent Channel3 call, even for unrelated searches. This is a non-obvious stateful behavior beyond the annotations, and it is clearly disclosed.

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 concise and well-structured: it opens with the primary purpose, then gives usage batching advice, notes the output format, and finishes with the mandatory thread_id rule. Every sentence is information-dense and contributes to correct invocation; there is no redundancy or filler.

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 an output schema present to handle return-value details, the description covers all essential operational context: scope of search, call batching, constraint placement, and the persistent thread_id requirement. It is fully sufficient for an agent to use the tool correctly, including across multiple calls.

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?

The input schema already provides comprehensive descriptions for all three parameters (100% coverage), so the description does not need to add much. It only reinforces that constraints go into `query` and that thread_id is required after the first call. This meets the baseline for high schema coverage but adds no new parameter-level semantic detail.

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 clearly states the tool's function: 'Search 100M+ products across thousands of retailers for one product type.' It specifies the resource (products), the action (search), and the scope (one product type), and distinguishes from sibling tools by emphasizing single-type search. The return of 'up to 8 product cards plus structured product data' further clarifies the purpose.

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 provides explicit usage instructions: 'Call once for each distinct product type, and send independent calls together' and 'Put relevant constraints in `query`.' It also mandates the thread_id propagation. However, it does not explicitly name alternative tools or describe when not to use this tool, so it falls short of a 5.

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