compare_pack_valuesCompare 2 to 25 shopping or procurement offers with compatible dimensions and currency, including shipping, tax, discount, yield and dilution adjustments.
| Name | Required | Description | Default |
|---|---|---|---|
| offers | Yes |
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, and it does disclose that the comparison accounts for shipping, tax, discount, yield, and dilution adjustments. It also notes the compatibility requirement for dimensions and currency. However, it does not describe what the tool returns (e.g., ranking, best offer, savings) or any side effects/assumptions, leaving an important behavioral gap.
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 a single sentence with no filler, front-loading the essential action and the offer-count range. The list of adjustments is compact and informative. It loses one point because the information is densely packed without any structural signposting for parameter rules.
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 tool has a nested offers schema, no annotations, and no output schema, so the description needs to explain both invocation requirements and expected results. It explains the input scope but omits the output shape, comparison criteria, and behavior when offers are incompatible. An agent would still have to guess what 'compare' yields.
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. It lists several financially meaningful parameters (shipping, tax, discount, yield, dilution), giving the agent some semantic grounding. It does not explain the role of text, label, price, or currency, nor how the adjustment fields interact, so compensation is partial.
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 verb and resource: comparing 2 to 25 shopping or procurement offers. It also names the included adjustments (shipping, tax, discount, yield, dilution), which distinguishes it from more general calculation tools. However, it does not explicitly contrast itself with the sibling tools, so it stops short of a 5.
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 implies when to use the tool (when comparing multiple offers) but gives no explicit guidance about when to prefer a sibling tool such as normalize_pack_value or calculate_real_discount. There are no exclusions, prerequisites, or alternatives mentioned.
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 targets a specific calculation, but several overlap on concepts like effective unit price and discount percentage. The descriptions are helpful, yet an agent could hesitate between normalize_pack_value, calculate_delivered_unit_cost, and calculate_buy_x_pay_y when trying to determine unit cost.
Most tools follow a consistent calculate_* pattern, with compare_pack_values and normalize_pack_value as readable variations on the verb-noun structure. All names are snake_case and clearly action-oriented, so the set feels predictable despite minor inconsistency.
Six tools is well-scoped for a pricing and pack-value domain. Each tool covers a distinct calculation need without redundancy or excessive surface area.
The set covers unit cost normalization, delivered cost, promotions, discount amounts, dilution, and multi-offer comparison, forming a complete toolkit for common pack-value analysis. No critical missing operation is apparent for the stated purpose.