Watch a price

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

With no annotations, the description carries the behavioral disclosure burden. It transparently states that calling the tool starts tracking the URL, records an initial observation, supports an optional target, and is re-read via watch_refresh. This makes the side-effecting, stateful nature of the tool clear without relying on annotations.

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 three short sentences with no filler. It front-loads the core instruction and rationale, then compactly summarizes the watch lifecycle and the relationship to watch_refresh. Every sentence contributes useful information.

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?

Given the simple parameter set, no annotations, and no output schema, the description is largely complete: it explains what the tool does, why it exists, what side effects occur, and what to call next. It does not mention the return value or any watch identifier needed for later operations, but this is a modest gap for a straightforward creation tool.

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 already describes all four parameters with 100% coverage, so the baseline is 3. The description adds little beyond restating that a product URL is the input and that a target is optional; it does not provide additional format, constraint, or interaction details beyond the schema.

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 states a clear action: 'Starts tracking it' for any product URL, with an explicit first observation and optional target. It differentiates itself from a generic web fetch tool by explaining that generic fetching returns raw HTML without the price, and names watch_refresh as the follow-up action.

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 guidance: call this tool for product URLs when a generic web tool would be insufficient because it returns raw HTML without the price. It also points to watch_refresh for re-reading. It does not discuss when to prefer related tools like price_check or price_add_manual, but the core when/why is clear.

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