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 discloses idempotency guarantees, the side effect of rewriting the breadcrumb, the per-concern result shape with inline upstream error text, and an explicit authorization requirement (operator-only, nsec-signed proof). These are exactly the behavioral facts an agent needs before calling a restricted mutation/recovery tool.

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?

Purpose is front-loaded in the first sentence, followed by diagnostic context, behavioral guarantees, and authorization in a logical order. The prose is slightly dense with coined vocabulary ('breadcrumb', 'step per concern') but each sentence adds information rather than repeating the title or schema.

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 restricted, idempotent recovery tool with an output schema, the description covers purpose, trigger condition, authorization, side effects, and error reporting without needing to restate return values. The remaining gap is the undocumented dpop_token parameter, which is the one thing an agent must supply to authenticate.

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?

The schema defines a single parameter, dpop_token, with 0% description coverage, so the description must compensate and it largely does not — the parameter is never named or explained. The only hint is the general 'requires proof (nsec-signed)' line, which gestures at authentication but does not tie it to dpop_token or explain its format/default. An agent can guess, but the semantics remain under-specified.

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 — re-preparing the operator's database schema — and frames it as a diagnostic/recovery action, which is far more than a restatement of the title. It also names the triggering symptom (Neon answering 4xx), so an agent can tell it apart from the other restore/recovery siblings. The unexplained term 'breadcrumb' is clarified later in the text, so it does not block comprehension.

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 condition for use: when Neon returns 4xx errors and a table or grant is suspected missing. That is a clear 'when to use' context, and the note that a clean re-run is harmless reinforces that it is safe to invoke liberally. No alternative tool is named for the same symptom, so it stops short of full alternative routing.

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