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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, and the description adds the consequences those hints cannot express: numbers persist 90 days with history, are restartable exactly once, and quota is not refunded. This is exactly the before-you-commit context an agent needs.

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?

Four short fragments, front-loaded with the WRITE marker and the batch cap, then retention rules and the endpoint. No sentence is filler.

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?

Covers scope, limits, side effects, reversibility and endpoint for a single-parameter tool with no output schema. It omits only failure/partial-batch behavior, which is a minor gap given the annotation coverage.

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 description conveys the maxItems=10 constraint and confirms the payload is a list of tracking numbers, but says nothing about the optional carrier field or the accepted number format. With reported schema description coverage at 0% for the top-level parameter, this only partially compensates.

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?

States a specific verb and resource ('stop tracking registered numbers'), marks it as a WRITE operation, and quantifies the batch limit. It is immediately distinguishable from siblings like track17_register_numbers and track17_retrack.

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?

Explicitly names the alternative path (track17_retrack) and the condition under which it applies ('can be restarted ONCE each'), plus the caveat that stopping does not refund quota. It stops short of stating when NOT to stop tracking (e.g., use list_tracking_numbers first) but gives clear selection context.

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