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

Annotations only supply destructiveHint=true; the description goes far beyond by disclosing that points are deducted, the reward is issued, the response's points_purchase.reward_fulfillment usually holds a discount code, the operation is irreversible, and it requires the points_purchase:write scope. Rich, decision-relevant behavioral context.

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 critical WRITE/spends-points warning, then layers usage, parameter conditions, irreversibility, scope, and endpoint. Every sentence earns its place with no 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?

For a destructive, no-output-schema mutation, the description covers safety, parameter conditions, irreversibility, the compensating tool, auth scope, and returns. Nothing an agent needs to call it safely is missing.

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, but the description adds usage semantics for points_to_spend beyond the schema field text: pass it for 'variable' products and leave it out for 'fixed' ones, clarifying the conditional requirement beyond what the schema states.

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 (redeem/purchase) and resource (points product) with a clear scope: it spends the customer's points and issues a reward. It distinguishes itself from read-oriented siblings like smile_get_points_product and smile_list_points_products by explaining the mutation it performs.

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 when-to-use ('only do this when the customer asked for it'), a when-not/irreversibility warning ('no API to cancel a redemption'), and names the alternative (smile_create_points_transaction) for compensating mistakes. This is the strongest tier of usage guidance.

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