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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, so the safety profile is covered. The description adds behavior the annotations do not: the DDL/DML scope, the data-disclosure risk, and the mandatory BEON PASS approval gate. It still omits what the operation returns and any transaction/rollback semantics.

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 short sentences, front-loaded with the core action before the caveats. Minor redundancy between 'before approval' and 'before execution' and no wasted filler, though it could be tightened.

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 high-risk DDL/DML tool with no output schema and 9 undocumented parameters, the description covers the essential intent and the approval gate, which is critical. However, it leaves the agent without the mechanics for the non-obvious fields (approval_id, beon_context, beon_environment), so an agent could not reliably construct a valid call from this description alone.

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 9 parameters, so the description carries the full burden and largely fails. It alludes obliquely to a 'query' and an approval ('selected project', 'approve the exact request'), but never explains the query format/size limits or how an agent obtains and supplies approval_id and the five beon_* parameters.

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 ('Execute SQL on the selected project') and scopes it with 'including DDL and DML', which distinguishes it from read-oriented siblings like supabase_list_tables. It does not explicitly name an alternative such as supabase_apply_migration, so an agent must infer the boundary, but the purpose itself is unambiguous.

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?

Gives clear, actionable context: it warns to review data disclosure and destructive effects, and states the operation requires explicit user approval in BEON PASS before execution — a genuine precondition an agent must satisfy. It stops short of naming when to prefer a sibling (e.g., apply_migration vs ad-hoc SQL), so it is clear context without alternatives.

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