find_customerSearches customers in the business by name and/or phone. Returns up to 20 matching customers sorted by name.
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | Customer name substring to search (case-insensitive). | |
| phone | No | Customer phone number or partial number to search. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare read-only, idempotent, and non-destructive behavior. The description adds meaningful behavioral traits: a result limit of 20, sorting by name, and search by name/phone. This goes beyond annotations to set expectations about response size and ordering.
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, tightly worded sentence with all key information front-loaded. No redundant or filler content.
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 optional-parameter search tool, the description adequately covers purpose, criteria, and return characteristics. It notes the result limit and sort order, which is sufficient given the lack of an output schema. Minor omission is lack of detail about returned fields, but overall it is complete for typical use.
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 schema covers both parameters thoroughly with descriptions (100% coverage). The tool description merely restates that search is by name and/or phone, adding no new parameter-level meaning. Baseline of 3 is appropriate.
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 uses the specific verb 'searches' and identifies the resource 'customers in the business.' It clearly specifies search criteria (name and/or phone) and distinguishes this from sibling tools like list_suppliers or query_sales.
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 usage for looking up customers by name or phone, but it does not explicitly contrast with alternatives or state when not to use. No exclusionary guidance is provided, though the intended context 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 duplicate the same underlying data in different presentation modes (get_payment_intent_status vs open_cobro_status, query_catalog vs open_catalog_selector, connection_status vs open_onboarding), creating ambiguity. Descriptions mention 'widget' vs JSON but an agent could easily pick the wrong one for a given task.
Tool names mix Spanish and English (caja_consultar_saldo vs validate_cuit) and use varying verb prefixes (open_, query_, get_, list_, find_, track_, quote_, validate_); only the open_ prefix is consistent.
22 tools sits at the high end of the borderline range; the server covers multiple domains (catalog, shipping, payments, fiscal) which justifies many tools, but some widgets and query equivalents could be consolidated.
The surface is heavily read-only: there are no create/update/delete tools for customers, suppliers, or products, and the only way to register a sale is through a widget that fires an internal function. There are also no tools to actually create a payment link or charge, leaving transactional workflows incomplete.