watch_querySave a query and later ask what has appeared since you last checked. Pull-based: nothing is pushed to you, you call check_watch when you want to know — which fits an agent that runs on its own schedule.
Use for monitoring: a topic, a competitor, a regulation, a product.
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | ||
| label | No | ||
| query | Yes | ||
| category | No |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds meaningful behavioral context beyond the annotations: it is pull-based, nothing is pushed, and the agent must call check_watch later. It also implies persistent state (saving a query for later comparison). The idempotentHint and readOnlyHint=false are consistent with this framing.
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 compact and every sentence serves a purpose: the first explains the mechanism, the second contrasts with push-based alternatives, and the third lists concrete use cases. No filler or redundancy.
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?
The description captures the core behavior and usage context well, but it leaves important gaps: parameter semantics for three of four fields are unspecified, and with no output schema, the agent gets no guidance on what check_watch returns or how results are delivered. Adequate for a simple tool, but not 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 description coverage is 0%, so the description should compensate, but it only meaningfully clarifies the 'query' parameter via examples (topic, competitor, regulation, product). It does not explain 'lang', 'label', or 'category', leaving the agent to guess their roles and valid values.
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 a specific action ('Save a query') and its purpose ('later ask what has appeared since you last checked'). It also distinguishes itself from the related check_watch sibling by explicitly describing the pull-based model.
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 concrete use cases: monitoring a topic, competitor, regulation, or product. It also explains when this tool fits — an agent that runs on its own schedule — and points to check_watch as the companion call. It does not explicitly list exclusions or alternatives like search, but the guidance is clear enough.
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.