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

Annotations flag destructiveHint=true, but the description goes well beyond that: no undo from here, calling it twice creates a duplicate refund (idempotency warning), merchant confirmation required, and it is not a money movement. These are high-value operational facts the annotations cannot express.

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?

Front-loads the core action then layers warnings; every sentence carries distinct information (scope, id source, confirmation/irreversibility, non-effects). The heavy capitalization is slightly noisy but functionally clarifying rather than filler.

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 single-parameter tool with no output schema, the description supplies everything an agent needs: precondition, input source, irreversibility, idempotency risk, human-confirmation gate, and explicit non-behaviors.

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 'not an order id', so the description's repetition alone would only rate baseline 3. It earns a 4 by naming get_refunds as the actual source of the identifier, which the schema does not state, closing the most likely invocation error.

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 (push/sync), resource (refund), direction (Final POS → connected WooCommerce store) and the resulting effect (online order shows as refunded). An agent can distinguish it from hub_sync_order_to_ecommerce and hub_get_refunds without opening any schema.

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?

Explicitly scopes when to use it: only for a refund that ALREADY exists in Final POS, with the id sourced from get_refunds. It also names the when-not conditions (does not move money, does not create the POS refund — that is done on the terminal), which is exactly the exclusion guidance needed.

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