run_query

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

Adds substantial context beyond annotations: the job can incur Google charges, it never exceeds the configured byte ceiling (fails rather than overruns), returns a job reference immediately (async), and resubmission creates new work rather than polling. The annotations only say non-read-only, open-world, non-idempotent, non-destructive; the description gives the cost and ceiling semantics an agent needs.

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, front-loaded with the risk (charges) and the key constraint (byte ceiling), followed by the return shape and routing guidance. Every sentence earns its place.

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?

An output schema exists, so return values needn't be detailed, yet it still states a job reference comes back immediately. Cost, ceiling, polling, and cross-project semantics are covered; only the account/location parameter meanings are left implicit.

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 coverage is 0%, so the description carries the burden. It clarifies two parameters well — project_id as the billing/job project that need not match the data's projects, and the byte ceiling behavior tied to maximum_bytes_billed. But sql, account, location, and parameters get no explanation, leaving meaningful gaps.

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 verb and resource — submit a SELECT job — and its two-phase nature (dry-run first). It differentiates from siblings by name, both the internal dry-run step versus dry_run_query and the polling handoff to get_query_results.

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?

Explicitly routes the agent: use get_query_results to poll and paginate, and 'do not resubmit to poll'. Also implies the dry-run-first workflow that distinguishes it from a plain submit. When/when-not coverage is unusually complete.

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