supabase_update_rows

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

No annotations are provided, so the description carries the full burden. It successfully communicates the safety guard (filter requirement) which is critical behavioral context. However, it lacks disclosure about return values (updated rows vs count), transaction atomicity, or whether partial updates are supported.

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?

Perfectly concise with two sentences and zero waste. The first sentence establishes purpose, the second delivers the critical safety constraint immediately. Front-loaded structure ensures the most important information (filter requirement) is impossible to miss.

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?

Given the tool has 5 parameters with nested objects and no output schema, the description provides minimum viable coverage by explaining the core operation and safety guard. However, the complete absence of parameter semantics and return value documentation leaves significant gaps for a mutation tool with complex inputs.

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?

With 0% schema description coverage, the description must compensate for all 5 parameters but fails to do so. While it mentions 'filter conditions' (mapping to the filters param), it provides no semantic guidance for critical params like 'data' (update payload structure), 'site' (project identifier), or 'use_service_role' (privilege escalation flag).

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 clearly states the tool updates rows matching filter conditions, using a specific verb and resource type. The '[UNIFIED]' prefix hints at cross-cutting functionality but isn't explained. It implicitly distinguishes from siblings like supabase_update_user (specific entity) vs this generic row updater, though it could explicitly mention 'table rows' to clarify the resource.

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?

Excellent explicit constraint: 'Always requires at least one filter to prevent accidental full-table updates' clearly states when-not-to-use (without filters) and implies the tool is for targeted updates only. However, it doesn't suggest alternatives for legitimate full-table updates (e.g., using supabase_execute_sql).

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