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

Annotations only provide destructiveHint=true; the description adds meaningful context beyond that — that the call writes a live tax/compliance record and adjusts tax owed, which tells the agent the effect is a real financial mutation, not just an 'add'. It omits permission requirements and irreversibility details.

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, no filler, with the write-behavior warning front-loaded before the mode-selection guidance and the endpoint reference trailing as an implementation note. Every clause earns its place.

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 4-parameter mutation tool with no output schema and minimal annotations, the description covers the operation's nature, both modes, and the line-item structure requirement. Missing only peripheral details like auth requirements and how refund_processed_at defaults behave (though the schema notes the default).

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 description coverage is 100%, so all four parameters are already documented in the schema. The description reinforces the critical dependency (type="partial" requires line_items keyed by reference_product_id) but adds no syntax or format detail beyond what the schema provides; baseline 3 is appropriate.

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 ('RECORDS a refund against a transaction') and clarifies the operation's nature as a write ('this WRITES a live tax/compliance record'). It also names the sibling it is distinct from implicitly by scoping to creating rather than listing refunds (numeral_list_transaction_refunds exists).

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 explicit conditional guidance: use type="full" to refund the whole transaction, or type="partial" with line_items for a partial refund. It does not name sibling tools or state when *not* to create a refund, but the mode-selection condition is unambiguous.

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