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

Annotations only cover the safety profile (readOnly, idempotent, openWorld), so the description's disclosure of 15-minute result caching, the 1-request cost including cache hits, and free failed searches is genuinely additive operational context an agent cannot get elsewhere. It stops short of 5 because it does not describe the response shape or whether this is a synchronous call versus a job requiring get_result.

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 purpose and hard constraint ('No sold search') are front-loaded in the first two sentences, followed by caching and cost facts, then the docs link. Every sentence carries information, though the cost/caching detail is packed densely enough that it borders on reference material rather than tool guidance.

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?

For a 13-parameter search endpoint with no output schema, the description covers the things an agent most needs before calling: currency scope, pricing semantics, cache staleness, and per-call cost. The remaining gap is the return contract (row shape, cursor usage in practice, sync vs. polled via get_result), which the absence of an output schema leaves partly unaddressed.

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% with 13 well-documented parameters, so the schema already carries the semantics of q, sort, country, price bounds, cursor, etc. The description only echoes a few of these (up to 24 rows, US/Canada, seller asks) without adding syntax or format guidance the schema lacks. Baseline 3 applies when the schema does the heavy lifting.

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 (search Whatnot Buy It Now active listings) plus scope (one page, up to 24 rows, US or Canada sellers). The clause 'No sold search' explicitly carves out the sold-data variant, distinguishing it from siblings like ebay_sold, mercari_sold and poshmark_sold without the agent opening any 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?

'No sold search' is a clear when-not signal, and 'Prices are seller asks' tells the agent these are not transaction prices, which matters for comparability against the *_sold siblings. It does not name an explicit alternative tool or spell out when to prefer another marketplace endpoint, so it stops 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.