supabase_drop_table

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

No annotations are provided, so the description must carry the full behavioral disclosure burden. It successfully notes the irreversible nature but fails to explain critical behavioral aspects: what happens to dependent objects (constraints, indexes, views), the effect of the cascade parameter, error behavior if the table doesn't exist, or required authorization levels.

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 appropriately brief with two sentences and no redundant prose. However, the '[UNIFIED]' prefix appears to be metadata noise that does not add value for the AI agent. The warning about irreversibility is appropriately placed.

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 that this is a high-risk destructive operation with zero parameter documentation in the schema and no output schema provided, the description is dangerously incomplete. It omits essential safety context about the cascade parameter's behavior and the specific consequences of the operation beyond the generic 'irreversible' warning.

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?

With 0% schema description coverage across 4 parameters, the description completely fails to compensate. It does not explain that 'site' refers to the Supabase project identifier, 'name' is the table name, 'schema' refers to the PostgreSQL schema namespace defaulting to 'public', or that 'cascade' controls whether dependent objects are also dropped—critical information for safe operation.

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 action ('Drop (delete)') and target resource ('database table'), using standard SQL terminology. However, it does not explicitly distinguish this from sibling operations like `supabase_delete_rows` (which removes data but preserves structure) or `supabase_drop_column`, which could confuse users about the scope of destruction.

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?

While the description includes a 'Warning: This is irreversible' alert, it lacks explicit guidance on when to use this tool versus alternatives (e.g., truncating vs. dropping), prerequisites (such as required permissions or emptying tables first), or when the cascade parameter should be utilized.

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