Rotate this fmrl.site key

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

Beyond the annotations (destructive, non-idempotent, openWorld), the description explains the blast radius ('the old secret stops working at once, wherever it was used') and exactly what survives the rotation (prefix, pages, name, quota, linked browsers, connected apps, key ring). It also discloses edge-case behavior for a missing key and for the FMRL_API_KEY environment override, which is precisely the kind of context annotations cannot convey.

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 core action and the guard condition are front-loaded, and every sentence adds information. The preservation list and the trailing no-op caveat are dense but each clause is load-bearing; a small tightening of the long preservation enumeration would make it easier to scan.

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?

With zero parameters and an output schema already present, the description carries only what structured fields cannot: the trigger condition, the irreversibility of the old secret, what state is retained, and the no-op cases. Nothing an agent needs in order to invoke it correctly is missing.

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 tool takes no parameters, so the schema baseline is 4. There is nothing for the description to disambiguate, and it correctly does not invent parameter discussion.

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 opens with a specific verb and resource: 'Replace this machine's fmrl key secret with a new one and save it here.' It is unambiguous and immediately distinguishable from the sibling that performs a related but different operation (fmrl_redeem).

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 states the trigger condition explicitly ('Only call it when the person asked to rotate the key') and names the alternative path with its condition ('To take up a key rotated on fmrl.site, use fmrl_redeem with its code instead'). It also states the no-op conditions, so an agent knows when the call is pointless.

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