sql_endpoint_execute_query

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

Annotations partially cover the safety profile (readOnlyHint=false signals the query may write; destructiveHint=false marks it non-destructive), but the description adds no behavioral context of its own: no warning that arbitrary T-SQL can mutate data, no mention of the 1000-row default cap, no note on permissions or result behavior. There is also an unresolved tension: arbitrary T-SQL can be destructive in practice while destructiveHint=false, though the description itself does not contradict the annotations.

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?

A single 13-word sentence that front-loads the verb and target with zero filler or repetition. It conveys the core purpose efficiently without duplicating the schema's parameter documentation.

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 tool that executes arbitrary T-SQL with no output schema, key expectations are missing: no statement of the return shape (rows/columns), no note that non-SELECT statements may mutate data, and no explanation of the 1000-row cap behavior. The fully documented schema and annotations keep it adequate for basic invocation, but an agent cannot predict response semantics.

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 all six parameters are already documented with types, defaults (maxRows=1000, database defaults to item display name), and the itemType enum. The description's 'lakehouse or warehouse' wording merely echoes the itemType enum values and adds no further parameter-level meaning, so the baseline of 3 applies.

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 names a specific verb ('Execute'), a specific artifact ('a T-SQL query'), and a specific target ('a lakehouse or warehouse SQL endpoint'). The T-SQL qualifier and target scope distinguish it from execution siblings like graphql_api_execute_query (GraphQL) and eventhouse_execute_kql (KQL) without opening any schema.

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 makes the intended context clear — T-SQL against lakehouse or warehouse SQL endpoints — which implicitly routes the agent away from KQL/GraphQL/DAX execution tools. However, it never states explicit when-to-use conditions, nor does it name alternatives or exclusions, so routing is left to inference.

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