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

Annotations already indicate idempotentHint=true and destructiveHint=false, so the description doesn't need to restate those. The description adds meaningful behavioral context by defining what counts as saveable content and what must never be saved, which goes beyond the annotations. It doesn't describe side effects like overwriting existing memories, but the idempotent hint covers the core safety profile.

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?

The description is compact and front-loaded with the most important usage rule. Every sentence earns its place: the first sentence states the trigger, the second states the action and scope, and the third lists exclusions. No filler or repetition of schema details.

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 simple 2-parameter write tool with an output schema and strong annotations, the description covers the essential context: when to use, what to save, and what to avoid. The only minor gap is not explaining what happens on overwrite or how the memory is stored, but the idempotent hint and output schema mitigate that need.

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 the schema already documents both parameters thoroughly. The description reinforces the content rules and brand_id sourcing ('copy an exact accessible ID supplied by the host or list_brands'), which adds practical guidance beyond the schema's basic descriptions. The example values in the schema also help.

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 states a specific verb ('saves'), a specific resource ('one personal preference or business fact for this user and brand'), and explicitly distinguishes it from report results, temporary state, inferred facts, and credentials. It clearly differentiates from siblings like list_memories and delete_memory.

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?

The description gives an explicit trigger condition ('Use only when the user explicitly asks to remember something or clearly establishes a durable preference') and explicit exclusions ('Never save report results, temporary account state, inferred facts, or credentials'). This is strong when-to-use guidance that also prevents misuse.

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