safe_alter_table

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

Since no annotations are provided, the description carries full burden. It discloses that the output contains scriptSql, lock levels, and notes, and mentions transaction constraints. It lacks details on error handling or validation, but covers key behaviors.

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 plus a brief instruction, front-loaded with the core purpose. Every sentence adds value 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 high complexity and no output schema, the description adequately explains the recipe output (SQL, lock level, notes) and usage workflow. It could be more detailed on return structure, but is sufficient for most use cases.

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 0%, so description compensates by explaining the 'intent' parameter's kinds (e.g., 'add NOT NULL column with default'). This adds meaning beyond the bare schema structure, though it does not detail each sub-field.

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 converts a high-level intent into a multi-step zero-downtime DDL recipe. It lists specific intent types (e.g., 'add NOT NULL column with default') and explains the output format (SQL, lock level, notes), distinguishing it from siblings like execute_sql.

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 provides explicit workflow: use the recipe output with dry_run_sql_file then executeSqlFile. It warns about CONCURRENTLY operations outside transactions. However, it does not explicitly state when to use this versus direct ALTER TABLE or other mutation tools.

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