Run a read-only query

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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds genuinely new behavioral facts: writes are refused (an error condition the agent must anticipate), the result arrives as a table, and dry_run provides a cost-estimation path before execution. It stops short of mentioning authentication requirements, row-limit truncation behavior, or quota/cost limits.

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?

Two sentences, both front-loaded with the operative clause ('Run one SELECT…', 'Use dry_run…'), and no filler. The write-refusal safety note is short and appropriately placed second.

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 no output schema, the description correctly covers the return shape ('rows as a table'), and read-only semantics are covered jointly by annotations and the write-refusal sentence. The remaining hole is max_rows (what happens past the 10000 cap, truncation vs error) and any auth/project-scoping prerequisites.

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 75%, above the low-coverage threshold, so the schema carries most parameter meaning. The description's dry_run sentence largely restates the schema's own 'Only validate and estimate the bytes scanned' and adds nothing about max_rows, the one undocumented parameter (a real gap for controlling result size).

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 ('Run one SELECT in GoogleSQL'), the cardinality constraint ('one'), and the return shape ('return the rows as a table'). Nothing in the sibling set (list_*/describe_*/screenshot_*/build_report_link) can be confused with executing an arbitrary query, so the boundary is clear without opening schemas.

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?

It gives a workflow hint ('Use dry_run to check a query and how many bytes it scans before running it') but never says when to reach for run_query versus siblings like list_tables or describe_table, nor any exclusions. Usage is only implied by the tool's function.

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