Remember a fact

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

Annotations indicate it's a write operation (readOnlyHint false) and not destructive, but the description adds valuable specifics: it merges into existing Memory, never overwrites, and de-dupes on identical text. It also discloses the impact on future ads. This exceeds what annotations alone convey, though it doesn't cover every edge case (e.g., maximum size).

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 two sentences: the first establishes purpose with concrete examples, the second provides behavioral guidelines (lasting vs one-off, merge, de-dupe). It is concise, front-loaded with the core verb and resource, and every sentence earns its place without redundancy.

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 write-only tool with two parameters, no output schema, and no nested objects, the description covers everything an agent needs to call it correctly: what to save, how to phrase it, when it applies, and how it behaves (merge, de-dupe). It even notes the long-term effect on future ads. Nothing critical 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% with both parameters described, so baseline is 3. The description enriches the 'text' parameter by giving examples and clarifying that it should be a durable fact or preference, which is more specific than the schema's 'the fact/preference, concise'. It also hints at categories (Brand, Audience, Taste) without explicitly mapping to the category parameter, adding context beyond the schema.

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 clearly states a specific verb ('Save'), a resource ('durable fact or PREFERENCE... into the workspace Memory'), and the target domain (brand, audience, creative taste). It distinguishes itself from siblings like 'forget' and 'list_memory' by explicitly framing itself as the tool for saving lasting facts.

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 provides clear context on when to use it ('For lasting things, not one-off requests'), which implicitly tells the agent when not to use it. However, it does not explicitly name alternatives (e.g., 'use forget to remove facts' or 'use list_memory to see existing memories'), though that's a minor gap given the obvious sibling relationships.

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