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

Annotations already declare destructiveHint=true, openWorldHint=true, and non-idempotency. The description goes further by explaining what destruction means (the app expires within ~an hour and the network uninstalls it everywhere) and that confirm=true signs and pays a usually minimal update fee while false returns only the plan. That is real added behavioral context beyond the 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 tight sentences: purpose and mechanism first, then the confirm behavior. Every sentence carries information and nothing is repeated from the schema or annotations.

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 destructive, no-output-schema tool this covers the essentials: what happens to the app, the timing, the cost implication, and the preview/execute switch. It stops short of noting reversibility (can a cancelled app be restored?) or any caveats about the 'name' argument, but the picture is largely complete.

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 only 50%, but the description carries the most important non-obvious parameter: confirm=true signs/pays versus false which returns the plan. The two private-key parameters are documented in the schema itself, and 'name' is self-evident from the tool context, so the description largely compensates for the coverage gap.

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 gives a specific verb and resource ('Ends an app early') and explains the underlying mechanism (term update to expire within an hour, then network-wide uninstall). This clearly separates it from deploy/build/list siblings, though it never names the closest alternatives such as flux_control_app or flux_quote_app.

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?

The confirm=true/false split implies a preview-then-execute workflow, which is useful usage guidance. However, there is no explicit statement of when to choose this over flux_control_app (stop/start) or flux_quote_app, and no prerequisites or exclusions are given.

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