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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description adds genuinely new context: the data is computed from the top ~120 search results and is 'a snapshot of current listings, not total market data'. It also discloses a visible side effect — example products are rendered to the user as product cards — which an agent wouldn't know from the schema.

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 core definition is front-loaded in the first sentence, followed by trigger phrases and then caveats. The list of query phrasings is long and slightly repetitive, but each clause carries routing or scope information rather than 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, the description doesn't need to explain return values, and it covers scope, data provenance, and freshness limits well. It leaves minor gaps — how the budget/mid-range/premium bands are defined and what happens when no listings match — but nothing that would cause a mis-call.

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 query, max_price, min_price and category_ids are all documented with examples and units in the schema itself. The description adds no parameter-level detail beyond confirming the general shape of the query; 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 — 'what a type of product costs in India right now' — and enumerates the exact payload: price range, median, budget/mid-range/premium bands with brands and example products, plus which brands and stores sell it. An agent can tell this apart from price-history or product-lookup siblings from the description alone.

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?

Gives six concrete trigger phrasings ('how much does X cost', 'what should I pay for X', 'which brands sell X') and one explicit exclusion: use this rather than general knowledge because prices change daily. It stops short of naming sibling tools (e.g. get_price_history for trends, search_products for raw listings), so routing between similarly-scoped price tools is left to inference.

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