Translate NL to SQL

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Despite annotations already marking readOnlyHint=true, the description adds substantial behavioral detail: LLM provider sees a compact schema brief, returns JSON with sql/explanation, SQL passes through a safety allowlist rejecting writes/DDL/multi-statement, and return values include SQL, model rationale, and rows/columns/row_count. It also explains provider routing and default order.

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 dense paragraph with an example, front-loaded with the core purpose and followed by specific behavior, parameter details, and a usage example. It is longer than ideal but every sentence adds value, and the structure is logical despite the lack of bullet points.

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 complex tool with 8 parameters and an output schema, the description covers the main purpose, safety constraints, provider routing, table_filter, return values, and a concrete example. It does not explain max_rows or explain_preflight, but the overall picture is complete enough for an agent to invoke the tool correctly.

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 only 13%, but the description compensates by explaining `question`, `schema`, `execute`, `table_filter`, and `provider` (including default selection order). It does not cover `max_rows` or `explain_preflight`, but the added detail for the most important parameters is significant.

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 translates a natural-language question into a read-only PostgreSQL query against a schema, with a specific verb ('Translate') and resource ('schema'). It distinguishes itself from sibling query tools by noting it uses LLM providers and the same safety allowlist as run_select.

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 provides clear context for when to use the tool (natural-language-to-SQL translation) and mentions using get_server_info to check configured providers. It also explains the execute flag and table_filter scoping, but does not explicitly exclude alternatives or state when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.