Batch query results

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

Adds real context beyond the annotations: single execution, batches returned together, no continuation cursor, and an explicit warning that functions can have side effects, which is consistent with destructiveHint=true and readOnlyHint=false. The ORDER BY advice and the no-cursor caveat are exactly the kind of behavior an agent cannot recover from structured fields.

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?

Four short sentences, each carrying distinct information: scope, execution model, ordering guidance, side-effect warning. No repetition and the selection condition is front-loaded.

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?

With a full output schema and annotations covering the safety profile, the only thing the description must supply is the batch-versus-stream execution model, and it does that clearly along with the side-effect caveat. Minor gap: it never positions itself explicitly against execute_query, which is the sibling an agent will most likely confuse it with.

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%, including defaults, bounds, and the maxRows truncation caveat, so the schema already carries the parameter burden. The description adds only the ORDER BY reproducibility hint, which is behavioral rather than a parameter detail. Baseline 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?

States a specific capability: bounded SELECT/WITH executed once, returning batches in a single response with no cursor. That distinguishes it in substance from execute_query, but the sibling is never named, so the agent must infer the pairing from the tool name alone.

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?

"Use for bounded SELECT/WITH results valid inside a subquery" gives a positive selection condition, and "no cursor or incremental streaming" implicitly rules out paginated workloads. It stops short of an explicit when-not or a named alternative such as execute_query.

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