Start an asynchronous premium web search and return a job_id. Poll get_job until a terminal state.
| Name | Required | Description | Default |
|---|---|---|---|
| tags | No | ||
| query | Yes | ||
| country | No | ||
| freshness | No | ||
| use_cache | No | ||
| num_results | No | ||
| query_fanout | No | ||
| exclude_domains | No | ||
| include_domains | No | ||
| timeout_seconds | No |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / properties / query_fanoutAdded value: +{
+ "default": true,
+ "title": "Query Fanout",
+ "type": "boolean"
+}Input schema / properties / use_cacheAdded value: +{
+ "default": false,
+ "title": "Use Cache",
+ "type": "boolean"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With annotations already indicating non-read-only, open-world, and non-idempotent behavior, the description adds the crucial detail that the search is asynchronous and returns a job_id that must be polled via get_job. This is a behavioral trait not captured by the annotations, enhancing the agent's understanding of the workflow. It does not mention rate limits or auth, but the async pattern is well disclosed.
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 only two sentences long, front-loaded with the core action and output, and immediately directs the agent to the next step (poll get_job). Every word contributes value, with no redundancy or unnecessary detail.
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?
While the output schema likely covers return values, the tool has 10 parameters and the description only addresses the start-and-poll flow. Key parameter semantics are missing, as noted above. The description is minimally viable but leaves significant gaps for an agent to correctly configure the search options.
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 must compensate for explaining parameters, but it does not. The description only mentions the query implicitly and the returned job_id. Parameters like query_fanout, use_cache, and include_domains are left entirely to their titles, which may be ambiguous. The description adds no parameter-level guidance, making this a weak point.
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 that this tool starts an asynchronous premium web search and returns a job_id. The action is specific ('Start') and the resource is well-defined ('premium web search'), distinguishing it from siblings like get_job, start_crawl, and scrape_url.
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 provides clear workflow guidance: start the search, then poll get_job until a terminal state. This tells the agent exactly what to do after invoking the tool. However, it does not explicitly compare with alternatives like start_crawl or state when not to use this tool, so it stops short of a full 5.
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 has a clearly distinct purpose: start_crawl and start_search initiate different async operations, get_job polls their status, scrape_url returns content synchronously, and get_usage handles account details. No two tools overlap in functionality.
All tool names follow a consistent verb_noun pattern: get_job, get_usage, scrape_url, start_crawl, start_search. The verbs (get, scrape, start) clearly indicate the action, and the nouns identify the target resource.
Five tools cover the core workflows of this scraping/search service: two async starters, one poller, one synchronous scraper, and one usage checker. This is well-scoped without unnecessary redundancy.
The core lifecycle is covered: start async jobs, poll for results, retrieve synchronous content, and check account balance. Minor gaps exist, such as no explicit cancel/revoke job tool or a way to list historical jobs, but these are not critical for basic usage.