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

Annotations already flag destructiveHint=true and non-idempotent, but the description adds material context they don't carry: no new charge is made, the pack balance is cleared to zero, the action is irreversible, and an X-Entitlement-Key header is required. That is exactly the extra behavioral disclosure expected on top of annotations.

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 dense sentences with zero filler, front-loaded with the action and its trigger, followed by the safety/irreversibility note and then the call protocol. Every sentence carries information the agent needs.

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 no output schema, the description still covers everything needed to call correctly: auth header, irreversibility, the preview-then-confirm flow, and the guard value. Annotations handle the safety profile, and the description fills the remaining gaps.

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 alone justifies a 3, but the description goes further by explaining the coupling between the two params: preview with confirm=false, then pass the previewed total as expect_usd to confirm. It also notes the tip is refused if the total changed, which is a semantic constraint beyond the schema text.

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 (tip remaining unused credits plus pack balance to AUTOGROK Desk) and quantifies the scope. An agent knows exactly what action this performs and that it is unrelated to the sibling tools (brief, page_extract, url_probe, etc.), so no sibling differentiation is needed.

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?

Gives an explicit trigger condition ("When you're done with a pack") and spells out the required two-step call sequence: confirm=false/omitted to preview, then confirm=true with expect_usd. Nothing about when or how to invoke is left to inference.

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