Report data quality issues for a business. Use when you notice incorrect phone numbers, wrong addresses, outdated info, or closed businesses.
| Name | Required | Description | Default |
|---|---|---|---|
| type | Yes | Type of feedback: POSITIVE (correct data), NEGATIVE (wrong data), NOT_FOUND (business gone), PHONE_INVALID, WEB_INVALID, HOURS_WRONG, DUPLICATE | |
| comment | No | Free text description of the issue or suggested correction | |
| business_id | Yes | Business ID to report about |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate readOnlyHint=false and destructiveHint=false, so the agent knows this is a write operation. The description adds context about the types of issues but doesn't disclose side effects (e.g., whether feedback is moderated, if it's one-way). It doesn't contradict annotations, but given annotations are present, the description adds only modest value beyond stating the action.
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 two sentences, front-loaded with the primary action. Every sentence adds value: the first states the core function, the second provides usage triggers. No fluff or redundancy.
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 3 parameters and no output schema, the description adequately covers purpose and usage context. It could mention that feedback can include suggestions (comment field) or positive confirmation, but overall it's sufficient for an agent to understand when and how to invoke it.
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 100%, so the schema already fully documents all three parameters including the enum values. The description's examples (incorrect phone numbers, wrong addresses) map to those enum values but don't add new parameter-level details. Baseline is 3 when schema covers all parameters, and no additional semantic value is provided.
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 a specific verb ('Report') and a resource ('data quality issues for a business'), clearly distinguishing it from the sibling tools which are all about fetching or searching data. It unambiguously states what the tool does.
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?
It explicitly tells when to use the tool ('Use when you notice incorrect phone numbers, wrong addresses, outdated info, or closed businesses'). While it doesn't mention alternatives, no sibling tool serves the same purpose. It could also note that positive feedback (POSITIVE enum) is allowed, but the main use case is clearly defined.
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 has a clearly distinct purpose: get_business retrieves full details, get_rankings returns popularity rankings, search_businesses performs filtered searches, suggest provides autocomplete, list_categories and list_countries enumerate valid options, health_check checks API status, and send_feedback reports issues. No overlap or ambiguity.
Most tools follow a verb_noun pattern (get_business, get_rankings, list_categories, list_countries, search_businesses, send_feedback). However, 'health_check' is a noun phrase and 'suggest' is a lone verb without an object, introducing minor inconsistency.
With 8 tools covering search, details, rankings, autocomplete, enumeration, health check, and feedback, the count is well-matched to the directory's scope. Each tool earns its place without redundancy.
The tool set provides a complete workflow for discovering and retrieving business information: list available categories/countries, autocomplete input, search, get rankings, fetch full details, and report issues. No critical gaps are apparent for a read-only directory.