Poll a search started by a background-job tool. Returns {status:"pending"} while running; when status is "done" the same object carries the search payload. Poll every 3 to 5 seconds.
| Name | Required | Description | Default |
|---|---|---|---|
| jobId | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses return format ({status: 'pending'} or 'done' with payload) and polling behavior. No annotations provided, so description carries full burden. Lacks explicit mention of failure states or errors, but covers key behavior.
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, no wasted words, front-loaded with action. Every sentence adds value.
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?
Covers polling and basic response, but with no output schema and simple schema, could be more explicit about the full structure of the done response (e.g., what fields the search payload contains). Adequate for a simple 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?
Schema coverage is 0% (jobId has no description). Description does not explicitly describe jobId beyond implying it identifies the background job. No format, source, or validation info added.
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 the verb 'poll' and the resource 'search started by a background-job tool'. It distinguishes from sibling search tools by focusing on result retrieval.
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?
Provides explicit polling interval ('Poll every 3 to 5 seconds') and implies it should be used after a background job is started. Does not mention when not to use or alternatives, but context around siblings makes misuse unlikely.
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 serves a distinct purpose: background job polling, country-wide search, worldwide exploration, synchronous route search, and stopover itinerary generation. No overlap in functionality.
All tools use snake_case with consistent verb_noun pattern: search_* for queries and get_job_result for polling. The naming is predictable and clear.
Five tools is well-scoped for a flight search and stopover planner server. Each tool adds unique value without redundancy or unnecessary complexity.
The tool set covers core flight search needs (specific routes, country-wide, worldwide, stopovers) with both synchronous and asynchronous modes. Minor gaps like multi-origin search or advanced filters are beyond the stated purpose.