detect_regressed_queries

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, covering safety. The description adds value by naming the specific DMV (sys.dm_db_tuning_recommendations) and the nature of the output (plan forcing scripts), giving the agent a clearer picture of behavior beyond the annotations.

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, front-loaded sentence that is under 20 words and directly states the action and resource. No filler or redundant information.

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 an output schema present and read-only annotations, the description covers the essential behavioral context: it surfaces recommendations from a specific DMV and provides scripts. It is complete enough for a simple diagnostic tool, though it could mention prerequisites like automatic tuning being enabled.

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% (both database_name and window_minutes have descriptions). The tool description adds no further parameter-specific context; it merely provides the overall purpose, so it meets the baseline but doesn't exceed it.

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 uses the specific verb 'Surface' and clearly identifies the resource: automatic tuning regression recommendations from sys.dm_db_tuning_recommendations, including plan forcing scripts. This distinguishes it from siblings like get_top_queries or tune_query, though it doesn't explicitly contrast with them.

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?

No guidance is provided about when to use this tool versus alternatives such as get_top_queries, plan_health_review, or detect_parameter_sniffing. The description states what it does but not the intended scenario or exclusions.

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