open_catalog_selectorOpens the catalog selector — a graphical product picker (MCP Apps widget) that shows active products with prices (ARS) and stock. Side-effect-free (no sale, no charge).
| Name | Required | Description | Default |
|---|---|---|---|
| search | No | Optional name filter (case-insensitive substring match). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds valuable context beyond those by explicitly stating 'Side-effect-free (no sale, no charge)' and specifying that it shows active products with prices (ARS) and stock, which is behavioral information an agent needs.
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 concise sentences, front-loaded with the main action. The first sentence clearly states the purpose and key details, the second handles side-effects. No redundant wording.
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 tool with only one optional parameter and no output schema, the description covers what it does, what it shows, and that it is side-effect free. The complexity is low, so this is 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?
The input schema fully documents the single optional 'search' parameter with a clear description (case-insensitive substring filter). The tool description adds no extra param semantics, so the baseline of 3 is appropriate given 100% schema coverage.
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 states a specific verb ('Opens') and a concrete resource ('catalog selector — a graphical product picker (MCP Apps widget)'). It distinguishes from siblings like query_catalog by emphasizing it is a graphical picker widget, not a data query, and clarifies it shows product prices and stock.
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 gives clear context: this is for launching a graphical product picker, useful when a user needs to visually select an active product. It does not explicitly name alternatives or state when not to use it, but the widget nature and 'MCP Apps' hint suffice for most use cases.
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.
Multiple tools have overlapping purposes, such as caja_registrar_movimiento vs register_movement, get_payment_intent_status vs open_cobro_status, and adjust_stock vs stock_load. The distinctions are not immediately clear from names/descriptions, causing a high risk of misselection.
Naming is inconsistent: mixes English and Spanish (caja_*, emit_invoice, send_whatsapp_*), and uses different patterns (open_*, get_*, query_*, list_*, etc.). Some names like stock_load and bulk_price_update don't follow a clear verb_noun convention.
50 tools is excessive for most contexts, even for a broad ERP-like domain. Many are UI widgets (open_*) that add clutter and could be consolidated, making the tool set feel heavy and harder to navigate.
The tool set covers many core business functions (products, suppliers, customers, sales, invoicing, shipping, cash register, payments, integrations). However, there are noticeable gaps: purchase requests have only create (no list/update/delete), shipments cannot be updated/cancelled, and sales lack direct update/query by ID.