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

Annotations only supply destructiveHint=true; the description carries the rest of the burden. It discloses the negative-balance rejection rule, the reversibility strategy, customer-visible vs merchant-only field exposure, the required points_transaction:write scope, and the underlying endpoint. That is rich behavioral context beyond the single annotation.

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?

Five compact sentences, each carrying distinct information: modality, sign semantics, safety rule, undo path, field visibility, alternative tool, auth scope, endpoint. The most decision-critical facts (WRITE, add/deduct) are front-loaded with no 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?

With no output schema and only a destructiveHint annotation, the description supplies everything needed: write semantics, failure mode, reversal, permission requirement, and the alternative tool. Nothing an agent needs to invoke this correctly 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% and the description still adds meaning: it explains the sign convention as a business rule (positive adds, negative deducts, rejection when it would go negative) and clarifies the customer-visible vs merchant-only split between description and internal_note. It distinguishes which fields have side effects for the customer, going beyond the schema labels.

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?

The description opens with a specific verb+resource+modality ("WRITE: add or deduct points from a customer's balance") and immediately qualifies it as a manual adjustment with examples (goodwill credit, correction). It explicitly contrasts with the sibling smile_create_activity for action-based rewards, so an agent can route without opening sibling schemas.

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?

It states the when-to-use case (manual adjustments, not action rewards), names the preferred alternative for rewarding completed actions, and documents the undo path (create an opposite adjustment). Conditions and alternatives are explicit rather than inferred.

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