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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the safety profile is covered. The description adds the genuinely non-obvious behavioral fact that scheduling does not mean completion, which prevents an agent from assuming the work is done. It does not explain what happens to existing images or how to verify progress.

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?

Two short sentences with no filler, and the core behavior (background scheduling) is front-loaded before the confirmation instruction. Every clause carries an instruction 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?

For a destructive background maintenance action with no output schema, the description covers both major agent-facing risks: asynchronous completion and the confirmation gate. It leaves open how to check whether regeneration finished and what happens on repeat calls given idempotentHint=false, which are minor but real 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% and the schema already says confirm must be true only after explicit user confirmation, so the description's confirmation sentence largely restates structured data. site_id, the trickier parameter, gets no additional treatment beyond what the schema already provides. Baseline 3 applies.

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+resource pair: "Schedule shop thumbnail regeneration in the background." That is clearly distinct from the cache-clearing and lookup-table siblings, though it never names an alternative for contrast. The async qualifier further narrows what the tool actually does.

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 precondition: ask the user for confirmation before calling with confirm=true, which is actionable guidance an agent can follow. It stops short of saying when this tool is appropriate versus maintenance siblings like clearing the template cache, so it is clear context without exclusions.

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