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

Annotations declare the non-idempotent, non-read-only profile, and the description adds genuinely new context: the recalculation is asynchronous and takes a few minutes. It doesn't say what the agent should do while waiting or whether repeated calls queue/stack, so it stops short of a 5.

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 short sentences, zero filler, and the most important fact (this triggers an async refresh) is front-loaded ahead of the confirmation constraint.

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 zero-parameter, no-output-schema trigger action, the description supplies the essentials: what fires, that it's async with a multi-minute latency, and the confirmation precondition. Only the post-trigger expectation (e.g., poll get_stack_score) is left unstated.

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?

Zero parameters, so the schema has nothing to document and the description is not expected to explain parameter semantics. Baseline 4 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 and resource: 'Kick off a StackScore refresh.' The action semantics (trigger a recalculation) are clearly distinct from the read-only sibling suppco_get_stack_score, though no sibling is named explicitly.

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 gating condition: 'Only use when the user confirms they want to refresh.' This is a real when-to-use rule. It stops short of naming the alternative (get_stack_score) for agents that just want to read the existing score.

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