Check a price now

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

No annotations are provided, but the description itself discloses the core behavior: it fetches the page, extracts and reports price/currency/title/confidence, computes the change since the last check, and creates no watch. This covers side effects and output expectations, far beyond a bare 'check price' statement.

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?

Three sentences, each earning its place: the call instruction and comparison, the output list, and the key side-effect. The most important usage directive is front-loaded.

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 single-parameter tool with no output schema and no annotations, this description gives an agent everything needed to invoke it correctly and interpret results. It names return fields, states the non-persistent side effect, and explains why the tool exists despite generic web fetching.

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% and the schema already describes the url parameter as 'Product page URL, including https://'. The description adds only generic framing ('any product URL') without new syntax or format details, so the baseline 3 applies.

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 ('Call this tool'), a concrete resource ('any product URL'), and enumerates the returned data (price, currency, title, confidence, change since last check). The closing note 'It creates no watch' differentiates it from watch-related siblings, and the output list separates it from price_history/price_add_manual.

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 instructs when to call it: whenever a product URL needs a price, and contrasts it with a generic web tool that returns raw HTML. It does not name specific siblings as alternatives (e.g., 'use watch_add if you want monitoring'), so it gets a 4 not a 5.

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