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

With no annotations present, the description carries the full burden and does so well: it declares idempotency ('Every statement is idempotent, so a clean re-run is harmless'), a side effect ('the breadcrumb is rewritten at the end'), the return shape ('one step per concern, with Neon's own error text inline'), and the auth requirement (nsec-signed proof). These are exactly the traits an agent needs before invoking a recovery mutation.

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 blocks, front-loaded with what the tool does, then when to use it, then access constraints. Jargon like 'the breadcrumb' and 'one step per concern' adds some decoding cost, but there is little outright waste.

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?

An output schema exists, so return values need not be spelled out, and the description still sketches them. For a one-parameter, operator-restricted recovery tool it covers purpose, trigger, safety, auth, and output. The only real gap is describing the dpop_token parameter.

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 0% for the single dpop_token parameter, so the description must compensate. It gestures at the auth requirement ('requires proof (nsec-signed)') but never names or explains the parameter itself, leaving its format and role to inference. Partial compensation only.

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 states a specific verb and resource ('Prepare this operator's database schema again') and the tool's identity (schema restore) is clearly distinguishable from every sibling, none of which touch the database schema. An agent can identify it without opening the schema.

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?

It gives an explicit trigger condition: 'Diagnostic / recovery tool for when Neon keeps answering 4xx and the operator suspects a table or grant is missing.' It also scopes access ('RESTRICTED to operator'). No alternative sibling is named as a fallback, which keeps it just short of a 5.

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