execute_query

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

No annotations are provided, so the description bears full responsibility. It mentions safety checks but does not specify what they entail, what destructive actions may occur, or what the result format is. A query execution tool should disclose read/write behavior and error handling.

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 very concise: one sentence for the tool and two lines for parameters. It is front-loaded with the key purpose and safety aspect, with no unnecessary words.

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?

The tool executes arbitrary SQL, which has complex behavior, yet the description lacks information about return values, whether results are streamed, pagination, error codes, or specifics of the safety checks. With no output schema or annotations, this is insufficient for an AI agent.

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 schema has 0% coverage (no descriptions for parameters), but the description explains 'sql: The SQL query to execute' and 'project_id: Optional... defaults to first configured project'. This adds meaningful context beyond the raw schema types.

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 'Execute BigQuery SQL' which combines a specific verb and resource. Siblings like get_datasets and get_tables have distinct purposes, so this tool stands out as the execution tool.

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 mentions automatic safety checks and LIMIT clause management but does not explicitly state when to use this tool versus alternatives or provide exclusions. Usage is implied but not contrasted with siblings.

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