Compare two specific seats on the same aircraft side by side. Returns scores, notes, dimensions, and a recommendation for which seat is better. Use when someone asks "Should I pick 14A or 22F on the Southwest 737 MAX 8?" or is deciding between two seats.
| Name | Required | Description | Default |
|---|---|---|---|
| seat_a | Yes | First seat to compare (e.g., 14A) | |
| seat_b | Yes | Second seat to compare (e.g., 22F) | |
| config_id | Yes | Aircraft configuration ID |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses the return format (scores, notes, dimensions, recommendation), which is adequate for a read-only comparison tool. No side effects or permissions are mentioned, but none are expected.
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: first defines the tool's action and outputs, second gives a usage example. Every sentence adds value; no 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?
Given no output schema, the description adequately covers return values. The three parameters are explained in the schema. Sibling tools provide context for when to use alternatives. Minor gap: no mention of required preconditions like 'same aircraft side.'
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 100%, with each parameter having a basic description. The tool description adds contextual meaning (e.g., 'comparison of two seats on the same aircraft side by side') and examples like '14A' and '22F', going 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 specifies a unique verb ('compare') and resource ('two specific seats on the same aircraft side by side'), with clear output types (scores, notes, dimensions, recommendation). It distinguishes from siblings like 'rowhint_get_best_seats' which returns best seats overall.
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?
Explicit usage context is provided: 'Use when someone asks "Should I pick 14A or 22F on the Southwest 737 MAX 8?" or is deciding between two seats.' While not listing when not to use, the sibling tools imply alternatives for other seat-related queries.
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.
Tools are mostly distinct, with clear purposes like comparing seats, getting best seats, overview, score, windowless, etc. Slight overlap between get_best_seats and pick_seat, as both recommend seats but for different contexts (config vs. flight). Otherwise, each tool has a unique role.
All tools use the 'rowhint_' prefix and snake_case verb_noun pattern. Most are consistent (e.g., get_*, compare_*, pick_*), but 'help_me_pick' and 'seat_roast' break the pattern slightly with imperative phrases or noun-verb order. Overall, naming is clear and predictable.
With 8 tools, the server covers a reasonable scope for seat intelligence: overview, recommendations, specific seat info, comparison, and a conversational picker. The count is well-balanced, not too few or too many for the domain.
Core use cases are covered: best seats, specific seat scoring, comparison, windowless seats, and flight-based picks. Minor gaps include lack of a tool to list all seats on a config with full details, but the conversational picker and overview tool mitigate this. Overall, agents can accomplish key tasks without dead ends.