Calculate the optimal deal stack for a specific purchase at a specific brand. Combines base cashback earned + best redeemable perk + any active promotions to show total savings. Use after route_purchase to maximize value at the chosen brand.
| Name | Required | Description | Default |
|---|---|---|---|
| userId | Yes | User ID to check redeemable perks against their balance. | |
| brandId | Yes | The brand to optimize the deal for. | |
| purchaseAmount | Yes | Purchase amount in USD. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of disclosing behavior. It explains the calculation logic (base cashback + best redeemable perk + promotions) and implies a read-only operation via 'Calculate'. It does not detail return format or side effects, but the core behavioral context is present.
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 concise and front-loaded: the first sentence states the primary purpose, the second explains the components, and the third gives usage guidance. Every sentence adds value with no redundancy or fluff.
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?
For a simple calculation tool with three well-documented parameters and no output schema, the description covers the essential aspects: what it does, how it calculates, and when to use it. It lacks explicit return value details but the phrase 'show total savings' implies the output. Given the tool's simplicity, this 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%, and each parameter has a clear description (e.g., userId for checking perks balance). The tool description adds minimal extra meaning beyond the schema, only reinforcing that the calculation is specific to a purchase and brand. Baseline of 3 is appropriate given the schema already documents parameters.
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 tool's purpose with a specific verb ('Calculate') and resource ('optimal deal stack'), and distinguishes it from siblings by specifying 'for a specific purchase at a specific brand'. It also mentions combining base cashback, redeemable perks, and promotions, which gives a precise scope.
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 explicit usage context: 'Use after route_purchase to maximize value at the chosen brand.' This tells the agent when to invoke the tool relative to other actions. It does not explicitly list when not to use it or name alternative tools, but the contextual guidance is clear.
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.
Several tools have overlapping purposes, e.g., rsnc_agent_best_deals, rsnc_agent_route_purchase, and rsnc_agent_compare_cashback all help find the best purchase/reward option. Similarly, rsnc_agent_network_info, rsnc_agent_network_stats, and rsnc_agent_network_analytics provide similar network overview data with unclear boundaries.
All tools share the consistent 'rsnc_agent_' prefix, but the remainder mixes verb-first patterns (browse_perks, claim_reward, create_event) with noun-first patterns (brand_analytics, network_flows, perk_intelligence). This inconsistency makes the tool surface less predictable than a uniform verb_noun scheme.
With 45 tools, the server feels over-scoped for a rewards network. While the domain is broad, many tools are highly granular analytics variations, and the count exceeds the 25+ threshold, adding cognitive load and diminishing coherence.
The tool set covers the core lifecycle: brand discovery, onboarding, event/perk creation and updates, reward processing, user balance/stats, and redemption. Minor gaps exist, such as no delete operations for events/perks and no direct user listing, but agents can work around these.
