select_rows

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

No annotations exist, so the description carries the full burden. It mentions validation of identifiers and pagination but does not disclose return format, error behavior, auth requirements, or whether it mutates data. Incomplete but not misleading.

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?

A single sentence that is front-loaded with key attributes, no fluff, and every word adds value. Perfectly concise.

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?

Given the complexity of row selection with pagination and filters, the description covers main features but omits return format details (e.g., structure of rows, cursor for next page). Slightly incomplete but still helpful.

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 100%, so baseline is 3. The description adds context about bounded rows and typed filters but does not provide additional meaning per parameter beyond what the schema already explains.

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 explicitly states it selects rows with specific features: bounded, catalog-validated identifiers, typed filters, and keyset pagination. This clearly distinguishes it from sibling tools like execute_sql or mutation tools.

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 implies usage for filtered, paginated row selection but does not explicitly state when to use this tool versus alternatives like execute_sql for arbitrary SQL or list_relations for metadata. No when-not guidance is provided.

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