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

Annotations already declare a read-only, closed-world, non-destructive operation. Beyond that, the description discloses that SUMMARY returns the first 100 terms in PC order, FULL returns the complete list, that a parent lookup returns child ASINs and counts, and that variationType UNKNOWN means lookup was unavailable rather than the ASIN being standalone. It also defines what naturalIdx, searchFrequencyRank, and searchVolume mean, which the annotations cannot convey.

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 front-loaded with purpose, then proceeds logically through ASIN-type handling, detail levels, field definitions, boundaries, and an edge case. It is dense but every sentence carries information; the only minor redundancy is defining output fields when an output schema exists.

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 an output schema exists, the description needn't explain return structures, and it does not waste space doing so. It covers everything an agent needs to call correctly: required ASIN semantics, marketplace context, detail-level selection, the follow-up flow for parents, and the boundary against advertising/ABA trend data.

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 100%, so baseline is 3, but the description adds meaning: the ASIN may be parent, child, or standalone and callers do not need to know the type, and it explains when to choose FULL on the first call versus defaulting to SUMMARY. The detailLevel enum is already documented in the schema, but the timing/behavior guidance is valuable beyond it.

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 ('look up natural search terms for a marketplace ASIN') and implicitly separates itself from advertising search-term data by saying it does not return advertising bids or keyword trends. An agent can identify the tool's scope without opening the schema.

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?

Explicitly explains how to handle parent vs child vs standalone ASINs, what to do after a parent result (ask the user which child, then call this same tool), when to use SUMMARY versus FULL, and where to go instead for keyword trends (an ABA tool). This is a complete decision tree for the caller.

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