Supabase: Disable rls

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the description's added value is the concrete consequence: the effect is removal of ALL RLS protection, which is meaningful domain context beyond the flag. It still omits whether the change is reversible, whether existing policies are retained but inert, and what privileges are required to execute it.

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?

Two short sentences with the action front-loaded and the warning immediately after it; nothing is padded. The '[UNIFIED]' tag is the only wasted token.

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 mutation against a security feature, with no output schema and undocumented parameters, the description is thin. It conveys the danger but not the operational requirements (auth level, scope of site, default schema) needed to invoke it correctly.

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 three parameters (site, table, schema), so the description must carry the burden and largely fails. Only 'table' is indirectly named; 'site' (which project/instance) and the 'schema' parameter with its 'public' default are never mentioned.

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 ('Disable Row Level Security on a table'), so the action is unambiguous. It does not, however, distinguish itself from the sibling supabase_enable_rls or explain where it sits relative to policy-level tools; the '[UNIFIED]' prefix adds noise rather than differentiation.

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 when/when-not guidance: nothing says why an agent would disable RLS versus creating a policy, nor that the inverse tool exists. No prerequisites (service-role credentials, project scope) are stated, so the agent must infer that this is a deliberate hardening bypass.

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