get_price_history

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

No annotations are provided, so the description carries the full burden. It discloses error behavior (ToolError with stable token), the aggregation scope ('pooled across every store'), and the inclusive date semantics. It implies a read-only operation via 'get' but does not explicitly state idempotency or lack of side effects. Given the absence of annotations, the description is thorough, though a brief note on read-only nature would make it fully transparent.

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 well-structured with a leading one-sentence purpose, then a compact Args/Returns/Raises layout. Every sentence adds value—examples for product_id and dates, explicit defaults, and error detail—without redundancy. It is front-loaded with the core function and avoids fluff, making it easy to scan.

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?

There is an output schema, so the minimal 'Returns: Aggregated price-history stats' is acceptable since the schema provides structure. The description covers the usage prerequisite (search first), parameter details, aggregation behavior, and error conditions. The only minor gap is a lack of mention of any range limits or rate limiting, but that's not essential given the tool's simplicity and the existence of an output 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?

The input schema has 0% description coverage, so the description must fully explain each parameter. It does this exceptionally: product_id is defined as 'Opaque product id from a search hit' with a concrete example; from_date and to_date are described with format and inclusiveness, plus a default for to_date. This far exceeds what the bare schema provides and gives the agent all necessary context.

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 ('Get aggregated price-history stats') and clearly scopes it to 'one product over a date range'. It enumerates the exact statistics returned (min/max/avg/first/last price and net change), which distinguishes it from the sibling tool search_products, which is about discovering products rather than analyzing history. This is unambiguous and actionable.

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 instructs the agent to 'Pair with search_products first and pass a hit's id here verbatim', establishing a clear workflow and the prerequisite. It also clarifies the required input source. While it doesn't state 'when not to use', the pair-with guidance and the fact that it's for a single product implies the alternative use case, making the routing clear.

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