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

Goes well beyond the destructiveHint/idempotentHint annotations: refunded conversions are terminal, the >5x-sale guard refuses with commission_above_sale and changes nothing, approval queues the commission for the next automatic payout run (Stripe only, at least a day later, PayPal/Wise paid by hand), and rejection removes it from the queue. The closing 'never sends money itself' sets the expectation for any agent tempted to report a payment as made.

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-loaded with the action and preconditions, then the refusal path, then side effects. It is long for one tool but nearly every clause carries operational weight; the Stripe/PayPal/Wise parenthetical is the one detail that could be trimmed without loss to tool selection.

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, idempotent mutation with no output schema, the description covers auth requirements, terminal states, the guard/confirmation loop including the returned error sentence, and downstream payout side effects. An agent has everything needed to call it safely and explain outcomes to a user.

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%, so the baseline is 3; the description adds real meaning on top by explaining the conditional workflow around confirmAboveSale (only after user confirmation of the returned sentence) and the consequence of the status choice on payout queues. conversionId semantics remain purely schema-level, which is fine for an identifier.

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 pair and resource ('Approve or reject a pending conversion'), immediately distinguishing it from create_conversion and list_conversions in the sibling set. The 'pending' qualifier further narrows the scope of what it acts on.

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 clear preconditions (Ultimate or Scale plan key with write access, conversion must be pending) and an explicit escalation path: set confirmAboveSale=true only after the user has seen the commission_above_sale message and confirmed. It does not explicitly route the agent away from sibling tools, but the precondition framing leaves little ambiguity about when this applies.

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