Skip to main content
Glama
Sign In

Rempa

by ai.rempa
OverviewDiscussionsAdmin

Compare a product with a competing product

compare_products
Read-only

Compare a tracked product head-to-head with one competing product AI names, over 7, 30 or 90 days: in the answers to questions that name neither, how often AI names both, only one or neither; each one's visibility, average position, how often each is named first when both are, sentiment, the typical price AI gives (median, as AI writes it) and the words about price; the same visibility per AI model and per update; and what AI says about each. Default competitor: the main one the brand picked, else the one named most. AI prices are never compared with the real price. Read-only.

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": {
      "project": "<project>",
      "product": "<product>"
    },
    "name": "compare_products"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNoThe period in days: 7, 30 or 90. Default 30.
productYesThe product: its id or its name, as returned by list_products.
projectYesThe project: its id or its address (for example "acme-france"), as returned by list_projects.
competitorNoThe competing product's name, as in get_product (competing_products). Default: the main competitor.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description still adds real behavioral context beyond them: the comparison basis is 'answers to questions that name neither', and it explicitly states AI prices are never compared with the real price, which pre-empts a likely misinterpretation of the returned price data.

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

Conciseness3/5

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

The core purpose is front-loaded, but the bulk is a single ~120-word sentence chaining metrics with semicolons, which is hard to parse. Listing the metrics is defensible because there is no output schema, though 'Read-only.' merely repeats the annotation.

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?

With no output schema, enumerating the returned measures (co-naming rates, visibility, average position, first-named rate, sentiment, median price and price words, per-model and per-update breakdowns) is necessary and mostly complete. Minor gaps remain around result format and how a missing product is reported, but nothing an agent needs to call it correctly is absent.

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, and the description goes slightly beyond by explaining what 'main competitor' actually means ('the main one the brand picked, else the one named most'). The days values and the id-or-name format are already fully documented in the schema, so no further credit is due.

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?

States a specific verb and resource ('Compare a tracked product head-to-head with one competing product') plus the time windows and the default-competitor resolution rule. No sibling does a head-to-head comparison, so an agent can distinguish it from get_product, get_perception and get_overview on the description alone.

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

Usage Guidelines3/5

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

Usage is implied by 'tracked product' and 'competing product', and the default-competitor rule tells the agent it can omit that parameter. But there is no explicit when-to-use guidance against get_perception or get_product, and no statement of prerequisites such as the product first needing to be tracked via add_products.

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

All Rempa toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources