Supabase: Delete policy

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

The annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, so the safety profile is covered by structured data. The description adds only the object type (RLS policy on a table) and says nothing about irreversibility, permission requirements, or the fact that policy behaviour for dependent queries changes immediately after deletion — the kind of context a destructive tool should carry.

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?

A single short sentence, front-loaded with the verb and resource, with no padding. It is terse rather than wasteful, though the '[UNIFIED]' token is dead weight.

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?

For a destructive, non-idempotent operation with four undescribed parameters and no output schema, the description is far too thin. An agent cannot learn from it which identifier disambiguates the policy, whether the site argument selects a hosted project, or what a failed deletion looks like.

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 0% across four parameters. The description does not mention site, table, name, or schema, nor clarify that 'name' is the policy name rather than the table name, nor explain what the default 'public' schema value means. With zero coverage the description must compensate and does not.

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?

States a specific verb and resource: 'Delete an RLS policy from a table.' That is unambiguous and, combined with the tool name and its create/update policy siblings, tells an agent which object class is affected. The '[UNIFIED]' prefix is unexplained jargon that adds no meaning, which keeps this just short of a 5.

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?

There is no guidance on when to use this versus supabase_update_policy or supabase_create_policy, and no prerequisites such as required permissions, whether the policy must be dropped/disabled first, or what happens if the policy does not exist. The agent must infer all routing from the tool name alone.

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