list_countriesList the ISO 3166-1 alpha-2 country codes supported for geo-targeting. Pass a model to get the codes available for that specific engine (some engines block certain countries).
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | Optionally filter to countries supported by a specific engine. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool as read-only, idempotent, and non-destructive. The description adds useful behavioral context not captured in annotations: some engines block certain countries, which explains why results may vary by model. This context supplements the structured annotations well.
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-loads the core purpose, and devotes the second sentence to the only optional nuance. There is no redundancy or filler.
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 zero-required-parameter read-only listing tool with an enum-only optional filter, the description covers purpose, the optional filter's effect, and behavioral nuance. No output schema is provided, but the description already states that the output is ISO 3166-1 alpha-2 country codes, so the context is sufficiently 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 already provides full coverage with a clear description for the model parameter and an enum of valid values. The description adds value by explaining why the parameter matters — filtering by engine-specific country support and warning that some engines block certain countries.
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 clearly states the action 'List' and the specific resource: 'ISO 3166-1 alpha-2 country codes supported for geo-targeting.' This makes the tool's purpose distinct from the sibling list_states and the various scrape_* tools.
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 explains the main use case — retrieving countries for geo-targeting — and provides clear guidance for the optional model parameter: pass a model to get engine-specific availability. It does not explicitly name alternatives or state when not to use this tool, so it falls just short of a 5.
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 targets a distinct engine or product (ChatGPT, Copilot, Gemini, Google, Google News, etc.), and the descriptions clearly specify what each scrape returns. The only potential overlap is between Google search and Google AI Mode, but the descriptions separate them effectively.
All tools follow a consistent snake_case verb_noun pattern: list_* for metadata and scrape_* for retrieval operations. The engine-specific names like scrape_chatgpt and scrape_google_ai_mode are predictable and easy to group.
Ten tools is a well-scoped size for a geo-targeted search and AI answer scraping server. Each tool covers a meaningful engine or metadata requirement without excessive redundancy.
The tool surface covers major AI assistants, Google search variants, news, and supporting geo-targeting metadata. Minor gaps exist such as no standalone Bing/DuckDuckGo scraper or explicit engine model listing, but the core workflows are well supported.