apply_expose

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

With no annotations, the description carries the full burden. It effectively discloses key behaviors: convergent (safe reapplication), revocation of dropped items, and dark-by-default tables. It does not cover error conditions, permissions required, or the exact response format, which would strengthen transparency.

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?

The description is concise (approx. 150 words), front-loaded with the core action, and structured logically. Each sentence adds value, with no redundancy. It efficiently covers purpose, behavior, and important caveats.

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 complexity of the input schema (nested objects, many fields) and no output schema, the description provides a solid overview of the tool's behavior and the manifest's effects. It covers the key points but could mention the response or side effects like RLS enablement to be fully complete.

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 coverage is 100%, so the schema already describes parameters. However, the description adds significant context beyond the schema: it explains the convergent nature and dark-by-default tables, which clarifies the overall semantics of applying the manifest. This justifies a score above baseline 3.

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's purpose: applying a declarative authorization manifest to a project. It includes the HTTP endpoint and explains the manifest's scope (tables, views, RPCs). It distinguishes from siblings like 'get_expose' and 'validate_manifest' by focusing on the application action.

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?

The description provides clear context on when to use this tool: to apply a manifest controlling authorization. It explains convergent behavior (no-op on reapply) and the dark-by-default rule for tables. However, it does not explicitly state when NOT to use it or mention alternative tools for checking or validating manifests.

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