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

The description states 'Pure data fetch (no AI analysis)', clarifying that this tool performs a direct retrieval without compute. The readOnlyHint annotation already declares this is a read operation, so the bar is lower; the description's honesty about the non-analytical nature adds useful context beyond what the annotation provides (that the data is raw and requires the agent to do interpretation). It could mention pagination or rate limits, but with annotation coverage this is solid.

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 two sentences plus a usage-dependent clause, all tightly packed with high-value information: what it returns, its non-analytical nature, sibling comparison, and interpretation guidance. No filler, every sentence adds meaning.

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 100% schema coverage, readOnlyHint annotation, and 5 parameters (1 required), the description covers purpose, differentiation, and usage interpretation adequately. It doesn't explain return value structure, but there is no output schema and the returned rows are described generically; for a search tool with this complexity, the coverage is good but could mention how results are ordered when no sort is specified (default revenue is in schema).

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 100%, so the schema fully documents all 5 parameters. The description adds modest value by clarifying sort order behavior (mentioning desc/asc interpretation is in schema already) and connecting the rows to interpretation guidance. Baseline 3 is appropriate since the schema does the heavy lifting and the description provides supplementary framing without duplicating schema details.

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?

Description states a specific verb+resource ('Keyword search against Amazon') and clearly specifies the returned data (price, sales, revenue, reviews, rating). It explicitly differentiates from sibling analyzeNiche by noting the difference between raw product rows and computed market aggregates. This is a strong, specific, and distinguishing purpose statement.

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 explicitly states when to use this tool ('Best when you need raw product rows with specific sort order or filters') and names the alternative (analyzeNiche) with its distinguishing behavior. It also provides concrete usage guidance on how to interpret the rows ('scan the rows for demand leaders, price clusters, and low-review listings that still sell'). This is exemplary usage guidance.

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