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

Annotations already declare destructiveHint=true, readOnlyHint=false and non-idempotent, and the description usefully reinforces the human-in-the-loop confirmation gate. However, it never explains what the recalculation overwrites, whether existing stored counts are discarded, or the scope of impact — the key unknowns for a destructive maintenance call.

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, action first, safety constraint second, with zero filler. The confirmation instruction is load-bearing rather than redundant padding.

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?

The simple two-parameter shape and full schema coverage mean little is required, and no output schema exists to explain. Still, for a destructive maintenance operation the description leaves the blast radius and post-call state entirely unspecified.

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%; both site_id and confirm are documented in-schema, including the list_sites prerequisite and the confirmation requirement. The description's confirmation sentence largely restates the confirm parameter's own description, adding workflow emphasis but no new semantics.

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 ('Recalculate product term counts'), which is unambiguous as an action. It does not explicitly distinguish itself from adjacent maintenance tools that also rebuild derived data (e.g. wc_maint_regenerate_product_lookup_tables), so an agent must infer the boundary.

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 one concrete procedural rule: obtain explicit user confirmation before calling with confirm=true. It offers no guidance on when recounting is warranted versus other maintenance operations, nor any prerequisite/context about which site state makes this appropriate.

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