supabase_execute_sql

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

With no annotations, the description carries the full burden. It successfully discloses the RLS bypass behavior and that it 'Returns query results', but omits details on transaction boundaries, timeout behavior, error handling, or required permissions.

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?

Three efficient sentences with no filler beyond the '[UNIFIED]' tag. Information is front-loaded with the action, followed by warning, then return value.

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?

Adequate for a high-risk operation given the RLS warning, but thin for a tool with zero schema documentation and no output schema. Should describe parameter formats or link to SQL syntax expectations.

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% and the description fails to compensate adequately. While 'Execute raw SQL query' implies the 'query' parameter contains SQL, the 'site' parameter (likely project identifier) is completely undocumented, leaving agents guessing whether it expects a URL, project ID, or nickname.

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?

Clear verb+resource ('Execute raw SQL query') that distinguishes this from structured alternatives like 'supabase_query_table'. The '[UNIFIED]' prefix is opaque metadata but doesn't obscure the core purpose.

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?

Provides critical safety guidance ('Use with caution - bypasses RLS') implying elevated privileges and security implications. However, lacks explicit guidance on when to prefer this over structured query tools or simple CRUD siblings.

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