Skip to main content
Glama

Compare products and case sizes

compare_generations
Read-onlyIdempotent

Spec diff between two products from a comparison table. Returns case_sizes_mm and size_variants per product. Select a_size_mm and b_size_mm for size-specific specs; unresolved values are null, never substituted with generation ranges. With no size selections, specs are generation summaries. Supports two sizes of the same model. Products also include verified buy_links.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "family": "<family>",
      "a": "<a>",
      "b": "<b>"
    },
    "name": "compare_generations"
  }
}

Input Schema

NameRequiredDescriptionDefault
aYesFirst product, e.g. 'fenix 8'
bYesSecond product, e.g. 'fenix 9'
familyYesTable id: flagships, running-flagships, bike-computers, hr-straps, recovery-wearables, polar-street, polar-loop, tactix, fenix, forerunner, forerunner-2xx, forerunner-entry, edge, edge-mid, varia, rally, instinct, venu, epix, enduro, vivoactive, descent, imini, quatix, marq, approach, coros-pace, coros-apex, coros-vertix, suunto-9, suunto-race, suunto-vertical, suunto-run, apple-ultra, wahoo-elemnt, wahoo-kickr, wahoo-tickr, wahoo-speedplay, wahoo-kickr-bike, polar-vantage, polar-vantage-m, polar-grit, polar-pacer, polar-ignite, polar-sensor, whoop, oura, hrm, amazfit-trex, amazfit-cheetah, amazfit-gtr, amazfit-gts, amazfit-active, amazfit-pace, amazfit-balance, amazfit-bip, edge-explore, tacx, coros-dura, edge-explore-3, forerunner-570-970, forerunner-70-170
a_size_mmNoFirst product's case size in mm, e.g. 47. Must match a recorded case size.
b_size_mmNoSecond product's case size in mm, e.g. 51. Must match a recorded case size.

Output Schema

NameRequiredDescriptionDefault
_viaYesSource attribution for Endurance Wire
specsYesEach row has values keyed by the products' comparison_label; null means unknown
familyYes
productsYes
changed_countYes
comparison_scopeYes
unresolved_countYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / family / description
      Previous value: -"Table id: flagships, running-flagships, bike-computers, hr-straps, recovery-wearables, polar-street, polar-loop, tactix, fenix, forerunner, forerunner-2xx, forerunner-entry, edge, edge-mid, varia, rally, instinct, venu, epix, enduro, vivoactive, descent, imini, quatix, marq, approach, coros-pace, coros-apex, coros-vertix, suunto-9, suunto-race, suunto-vertical, suunto-run, apple-ultra, wahoo-elemnt, wahoo-kickr, wahoo-tickr, wahoo-speedplay, wahoo-kickr-bike, polar-vantage, polar-vantage-m, polar-grit, polar-pacer, polar-ignite, polar-sensor, whoop, oura, hrm, amazfit-trex, amazfit-cheetah, amazfit-gtr, amazfit-gts, amazfit-active, amazfit-pace, amazfit-balance, amazfit-bip, forerunner-570-970, forerunner-70-170"New value: +"Table id: flagships, running-flagships, bike-computers, hr-straps, recovery-wearables, polar-street, polar-loop, tactix, fenix, forerunner, forerunner-2xx, forerunner-entry, edge, edge-mid, varia, rally, instinct, venu, epix, enduro, vivoactive, descent, imini, quatix, marq, approach, coros-pace, coros-apex, coros-vertix, suunto-9, suunto-race, suunto-vertical, suunto-run, apple-ultra, wahoo-elemnt, wahoo-kickr, wahoo-tickr, wahoo-speedplay, wahoo-kickr-bike, polar-vantage, polar-vantage-m, polar-grit, polar-pacer, polar-ignite, polar-sensor, whoop, oura, hrm, amazfit-trex, amazfit-cheetah, amazfit-gtr, amazfit-gts, amazfit-active, amazfit-pace, amazfit-balance, amazfit-bip, edge-explore, tacx, coros-dura, edge-explore-3, forerunner-570-970, forerunner-70-170"
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare this as a safe, read-only, idempotent operation. The description adds meaningful behavior beyond annotations: unresolved values are null and never substituted with generation ranges, and products include verified buy_links. These are useful disclosure details for interpreting output.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core operation and then covers size selection, null behavior, and buy links. It is dense but every sentence contributes useful information, with little wasted language.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so the description need not fully document return values, and it appropriately names key outputs. It covers size-selection behavior and null semantics well. The family parameter is not explained, but its large enum is fully listed in the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description still adds value by explaining the effect of omitting size parameters (generation summaries), the null behavior for unresolved sizes, and that size selections must correspond to recorded case sizes.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: a spec diff between two products from a comparison table. It clearly distinguishes itself from siblings like get_product and get_news by focusing on comparison outputs such as case_sizes_mm and size_variants.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explains the key usage decision: select a_size_mm and b_size_mm for size-specific specs, or omit them for generation summaries. It also notes that two sizes of the same model are supported. It does not explicitly name sibling alternatives, but the comparison-table framing provides clear context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources