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

Annotations already flag destructiveHint=true and idempotentHint=false, so the safety profile is known. The description adds genuinely new behavioral context beyond the annotations: that the change may restart Postgres and degrade production performance. It does not disclose the approval/auth requirement implied by approval_id, but the risk warning is real added value.

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, front-loaded sentences with zero filler: the action first, then the risk. Efficient for the amount of content present, though there is no structural framing for a tool with this many parameters.

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 production-database mutation the description covers the core risk but omits the approval prerequisite and any guidance on the config object's accepted keys. With short text and no output schema, the annotations carry much of the safety burden, so it is minimally but not fully adequate.

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, including a nested config object with five sub-fields (work_mem, max_connections, statement_timeout, etc.) that have patterns and bounds but no textual explanation. The description's generic "Change Postgres settings" only vaguely maps to the config parameter and explains nothing about project_ref, approval_id, or the beon_* metadata fields.

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+resource ("Change Postgres settings"), which clearly distinguishes a mutating config operation from the read-only sibling supabase_get_database_config. It stops short of naming that sibling or scoping which settings, but the purpose 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?

No when-to-use, when-not-to-use, or alternative tools are mentioned. The presence of a required approval_id parameter and an environment enum suggests an approval workflow, but the description gives no guidance on prerequisites or when this should be preferred over changing settings elsewhere.

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