supabase_run_sql

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

Without annotations, the description carries the full burden and does well: it discloses it's a 'LIVE write' requiring 'human approval', and enumerates destructive statement patterns (DROP, TRUNCATE, ALTER...DROP, GRANT/REVOKE on auth, DELETE/UPDATE without WHERE) that need approval. This is valuable behavioral context. However, it doesn't clarify what happens with non-destructive statements (auto-approved?) or the approval_id flow.

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 sentences, front-loaded with the core action and the critical safety caveat. Efficient, though the destructive-statement parenthetical is dense and could be slightly better organized.

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?

An output schema exists, so return values needn't be explained. The description covers the key risk profile (write, approval needed for destructive ops), which is the most important context for this tool. But with 0% param coverage and no annotation safety profile, the missing parameter documentation and approval_id mechanics leave gaps.

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%, so the description must compensate for all 3 parameters. It mentions no parameter semantics at all — not 'ref', not 'sql', not how 'approval_id' relates to the approval flow it describes. The approval concept is mentioned but never tied to the parameter that carries it.

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+resource: 'Run SQL on the project (schema/migration)'. The purpose is clear, but the parenthetical '(schema/migration)' is the only hint at intended use case, and there's no explicit differentiation from any sibling. It's clear but not sharply distinguished from other setup/config tools.

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 implies usage context ('schema/migration') and names approval requirements for destructive statements, but it gives no explicit when-to-use guidance or named alternatives. For a high-risk live SQL tool, this is merely implied usage rather than clear guidance.

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