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

Annotations already declare destructiveHint=true, openWorldHint=true and idempotentHint=false, so safety is largely covered. The description adds value beyond them by disclosing that the query is recorded permanently in migration history and that the user must approve the exact request in BEON PASS before execution, which the annotations do not state.

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 tight sentences with the core action front-loaded, followed by a requirement and an approval precondition. Nothing is padded, though the RLS sentence is a minor aside that 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 destructive migration tool the description covers the safety-critical approval flow and the persistence behavior, and no output schema exists so returns need not be explained. However, with 10 undocumented parameters and no format guidance for the SQL query, an agent still lacks enough to invoke it fully 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 10 parameters, so the description carries the full burden, yet it only loosely touches the approval flow ('approve the exact request in BEON PASS') without explaining approval_id, the beon_* infrastructure parameters, or the name/query formats. Notable parameters like beon_environment (staging/production) go entirely unexplained.

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?

The description gives a specific verb and resource: 'Apply SQL and record it in Supabase migration history', which distinguishes it from pure SQL execution by noting persistence in migration history. It does not explicitly name the closest sibling (supabase_execute_sql) or contrast with it, so it falls short of the 5-level sibling 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?

Usage is implied rather than stated: recording in migration history signals this is for durable schema changes, and 'Include RLS policies for exposed tables' hints at a precondition. But there is no explicit when-to-use / when-not-to-use guidance against supabase_execute_sql or a note on which changes belong in a migration.

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