get_tuning_session

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

The annotations already convey read-only, idempotent, non-destructive behavior. The description adds valuable context about the response containing redacted data and the guarantee that raw SQL is never persisted, which exceeds the annotation baseline.

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 a single concise sentence plus a brief privacy note, both conveying essential information without redundancy.

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 presence of an output schema and the tool's straightforward read-only nature, the description covers the return payload and key constraints. It does not mention prerequisites (e.g., session existence) but is otherwise sufficient for agent selection.

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 50% — session_id has a basic description and database_name is undocumented. The tool description does not clarify either parameter's format, defaults, or relationship, failing to compensate for the gap.

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 the tool's function: resuming a durable tuning session and enumerates the returned data (redacted leaderboard, evidence, events, remaining budgets). The verb 'Resume' distinguishes it from sibling tools like start_tuning_session.

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 existing tuning sessions via 'Resume', but does not explicitly state when to use it instead of alternatives like starting or finalizing sessions. There is no exclusionary guidance.

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