prepare_plan_action

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

The annotation readOnlyHint=true contradicts the description's 'persist' action, which implies writing state. Since the description explicitly says it captures and persists an intent, it is a side-effecting operation, clashing with the read-only hint. This is a critical inconsistency that misleads the agent about side effects.

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 extremely concise at two sentences, with key information front-loaded. Every phrase adds value: capturing state, persisting intent, and clarifying review-only ownership. No filler or repetition.

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 tool's complexity (11 parameters, nested objects, output schema), the description is too sparse. It does not explain the workflow context, how the persisted intent is used, or how it relates to sibling tools like dry_run_plan_action or plan_enforcer_tick. Annotations and output schema help, but the description's brevity leaves major gaps for an AI agent to safely invoke it.

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 description coverage is 64%, with several parameters (plan_id, query_hints, candidate_id, database_name) lacking descriptions. The tool description adds no parameter-level meaning, focusing only on the overall purpose. It fails to compensate for the undocumented parameters, leaving the agent uncertain about optional inputs.

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 captures Query Store control state and persists a reviewed, redacted plan-action intent, with a specific verb and resource. It also explains that Automatic Tuning ownership is review-only, which helps distinguish it from execution-focused tools, though it does not explicitly name competing alternatives.

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 as a preparatory, review-only step ('Automatic Tuning ownership is review-only') but does not explicitly state when to use this tool versus related siblings like dry_run_plan_action or review_plan_enforcement. There are no clear exclusions or alternative recommendations, leaving the agent to infer timing.

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