prepare_view_change

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

Annotations already declare readOnlyHint=true and idempotentHint=true, but the description adds meaningful behavioral context: preparations are process-local, sandbox preparations are restart-safe only with explicit raw-SQL state opt-in. This goes beyond the annotations and helps the agent understand the transient vs. persistent nature of the operation.

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 two sentences, front-loaded with the core purpose, and every phrase adds value (e.g., 'reversible', 'process-local', 'restart-safe', 'raw-SQL state opt-in'). No filler or redundant restatement of the title or schema.

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 (8 params, output schema present), the description covers the key novelty—reversibility and preview semantics—and differentiates preview types. It does not explain how to opt into raw-SQL state or what 'sandbox' refers to, but the presence of an output schema reduces the need to explain return values. Overall, it provides sufficient context for initial 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 description coverage is 50%, and the description does not compensate by elaborating on any parameters. It mentions 'CREATE VIEW or ALTER VIEW' which hints at the 'operation' parameter, but fails to clarify the meaning of 'definition', 'schema_bound', 'indexed_view', 'database_name', or 'idempotency_key'. With half the params undocumented and no description-level guidance, the agent receives insufficient parameter semantics.

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 specifies a clear verb ('Prepare and preview') and resource ('CREATE VIEW or ALTER VIEW change'), distinguishing it from siblings like execute_sql or explain_query. It immediately conveys that this tool handles view changes and provides a preview, which is a unique responsibility among the listed 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 previewing view changes but does not explicitly state when to use this vs. alternatives, nor does it mention exclusions (e.g., 'use this only for preparation, not for applying'). The reference to 'process-local previews' and 'sandbox preparations' gives some context but not a clear comparative guideline.

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