Execute arbitrary read-only SQL against the DuckDB database. Only SELECT and WITH statements are allowed. Use get_schema first to understand available tables and columns. Available on Professional tier and above.
| Name | Required | Description | Default |
|---|---|---|---|
| sql | Yes | SQL query (SELECT or WITH only) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description properly discloses the read-only nature and allowed statement types. It also mentions tier availability (Professional tier and above). However, it omits potential behavioral details like result size limits, timeouts, or how errors are surfaced, which could catch users off guard.
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 three concise sentences, each adding distinct value: what it does, what's allowed, and a prerequisite. No redundant information or fluff exists.
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 one-parameter tool with no output schema, the description covers the core functionality, constraints, and usage prerequisite. It lacks explicit details about return format or performance considerations, but given the arbitrary nature of SQL, these are less critical.
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 describes the 'sql' parameter with 'SELECT or WITH only', and coverage is 100%. The description adds minimal extra meaning beyond the schema, merely restating the read-only constraint. This meets the baseline but doesn't enhance parameter understanding.
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 tool 'Execute arbitrary read-only SQL against the DuckDB database' with specific constraints (SELECT/WITH only). This distinguishes it from the sibling query tools (e.g., query_investments, query_prices) which are purpose-built for specific data sets, making the purpose unambiguous.
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 users to use get_schema first to understand the schema, and restricts usage to SELECT and WITH statements, preventing misuse. While it doesn't name alternative tools, the mention of 'arbitrary' and the constraint to read-only SQL clearly implies this is for custom queries not covered by the sibling tools.
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 purpose: metadata (get_schema, get_data_freshness), generic SQL access (execute_sql), and domain-specific queries (investments, prices, production, trade, wells). There is no overlap between specialized queries, and execute_sql is clearly positioned as a raw fallback.
All tools follow a consistent verb_noun pattern: get_ for metadata, query_ for data retrieval, and execute_sql for the raw query tool. The style is uniform and predictable, making it easy to infer tool behavior from names.
With 8 tools, the set is well-scoped for the domain. It covers the core data dimensions (investments, prices, production, trade, wells) plus essential support tools (schema, freshness, raw SQL) without unnecessary bloat or redundancy.
The tool set covers all major facets of Argentine oil & gas data: production, investment, pricing, trade, and wells. The inclusion of execute_sql and get_schema ensures that any data not exposed via a dedicated query can still be accessed, leaving no obvious dead ends.
