preview_table

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds one genuinely new trait, "Row order is unspecified", but says nothing about pagination continuation via page_token, truncation, or the page_size ceiling (1000) enforced by the schema.

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 short sentences with zero waste; the core operation is front-loaded ahead of the caveat about row order.

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 need not be explained, and the read-only nature is covered by annotations. However, for a 6-parameter tool with no schema descriptions, the description leaves too much of the parameter surface unexplained to be fully complete.

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?

Six parameters with 0% schema description coverage, so the description carries the full burden and largely fails: project_id, account, dataset_id and table_id are undocumented, and page_token's continuation semantics are only implied by "bounded page". The one useful hint is that reads are paged, which maps loosely to page_size/page_token.

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?

A specific verb and resource (read a bounded page from a physical table) plus an explicit contrast with the query-based siblings ("without a SQL query job"). An agent can distinguish this from run_query/dry_run_query without opening a 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?

"Without a SQL query job" implies when this is preferred over run_query, but the guidance is only hinted at. There is no explicit when-not or named alternative such as get_table or run_query.

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