cancel_watchStop deliveries for a watch: the feed URL dies immediately and the webhook deactivates. Idempotent. Sourcing for an already-promoted product continues (shared watchlist state) — cancellation affects this watch's delivery only.
| Name | Required | Description | Default |
|---|---|---|---|
| watch_id | Yes | The watch_id returned by register_watch. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Adds context beyond annotations: idempotent, immediate feed/webhook deactivation, and that sourcing continues for promoted products. Consistent with destructiveHint and idempotentHint.
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?
Two sentences, front-loaded with main purpose, no redundant 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?
Explains key effects and idempotency. For a simple single-parameter tool with no output schema, the description is sufficiently complete.
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% with a clear description for watch_id. The tool description does not add further parameter detail beyond the schema, but none is needed.
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 clearly states 'Stop deliveries for a watch' and specifies immediate effects (feed URL dies, webhook deactivates), distinguishing it from sibling tools like register_watch and check_watch.
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?
Implied usage (cancel a watch) but no explicit when-to-use or when-not-to-use compared to alternatives. Does mention idempotent and scope, but lacks direct comparison with siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool maps to a distinct operation: discovery (get_deal, latest_deals, search_deals), watch lifecycle (register_watch, check_watch, cancel_watch), and feedback (report_outcome). The potential overlap between latest_deals and search_deals is resolved by their freshness/curation vs keyword-search framing. No two tools appear to do the same thing.
Six of seven tools follow a clear verb_noun pattern (register_watch, check_watch, cancel_watch, get_deal, search_deals, report_outcome). 'latest_deals' breaks the pattern by using an adjective_noun noun phrase instead of a verb, but this is a minor deviation. Overall the convention is predictable.
Seven tools is well-scoped for a deals discovery and watch-monitoring server. Each tool covers a distinct need and none feel redundant. This is within the ideal range and not bloated.
The core lifecycle is covered: discover deals, get details, register a watch, check its status, cancel it, and report outcomes. Missing a list/update watch operation is a minor gap, but cancel-and-re-register works as a workaround. For the stated purpose, no severe dead ends exist.