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

Annotations already flag destructiveHint=true and idempotentHint=false, and the description goes beyond them by disclosing operational downtime and possible irreversibility — the kind of consequence an agent must weigh before invoking. It stops short of stating whether a backup or approval is required to proceed.

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 with zero waste; the action is front-loaded and the risk warnings follow immediately. Nothing redundant.

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?

Covers the risk profile well for a destructive, non-idempotent operation with no output schema, but with 9 undocumented parameters and no named compatibility-check tool, an agent still lacks what it needs to call this correctly end to end.

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 adds nothing: project_ref (the 20-char project id), target_version (the version string), and the approval/beon_* fields are all unexplained. An agent cannot tell what target_version format is expected or what approval_id does.

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 ("Start a database upgrade") that an agent can distinguish from read-side siblings such as supabase_get_upgrade_status and supabase_get_upgrade_eligibility. It does not name those siblings explicitly, but the action/resource pair 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?

"Review compatibility first" implies a prerequisite but never names the tool that performs it (e.g. supabase_get_upgrade_eligibility), and there is no when-not guidance or mention of confirmation/approval flow. Usage is inferable but not spelled out.

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