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

Annotations already carry readOnlyHint=true/destructiveHint=false, so the bar is lower, but the description still adds substantial behavioral context: the per-call 500-item cap, the token-heavy cost of paging entire catalogs, default response shape (~14-field compact), and the response_format trade-offs (resale drops product_description to stay under token cap, full can exceed it). This is exactly the kind of operational context that exceeds structured fields.

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?

Four sentences with zero filler, front-loaded with the core function then moving to formats, cap, and the critical anti-pattern warning. Each sentence carries distinct information: what it does, what it returns by default and how to change that, its hard cap, and when NOT to use it with a pointer to the alternative.

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 38-parameter tool with no output schema, the description orients the agent well: purpose, sampling boundary, response formats, per-call cap, and pagination are all covered. The main gap is the absence of explicit sibling routing (e.g., get_retailer_product for single-product details, search_promotions for deals) — though this is minor since the tool's role is clearly scoped.

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 baseline is 3. The description adds genuine operational meaning beyond the schema: it explains response_format trade-offs (resale drops product_description 'best for screening a whole catalog without exceeding the token cap'), frames 'after' within cursor pagination, and states the 500-item cap that contextualizes limit. This is modest but real added value, justifying a 4.

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 opens with a specific verb+resource: 'Search and SAMPLE a retailer's catalog' and enumerates concrete capabilities (text search, barcode lookups, price/discount filtering, cursor pagination). It sharply distinguishes the tool from the bulk-export use case, making its scope unambiguous even without reading 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?

The description gives explicit when/when-not guidance: 'this tool is for finding and sampling products, NOT bulk export' with the reason (slow and token-heavy) and a named alternative (LemMeBuyIt direct REST bulk API). It also guides response_format selection by task. It stops short of routing to sibling tools like get_retailer_product for single-item lookups or search_promotions, so it doesn't hit 5.

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