Remember a fact

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

The description adds meaningful behavioral detail beyond the annotations: it merges into existing memory, never overwrites, de-dupes identical text, and refuses certain content types. These are non-obvious effects an agent needs to predict the outcome of a call, and they do not contradict the readOnlyHint or destructiveHint values.

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 core purpose is front-loaded, followed by examples and then merge/refusal semantics. Every sentence contributes a distinct piece of guidance, and there is no filler or redundant restatement of the schema.

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 two-parameter write tool with no output schema, the description covers what to save, what never to save, how duplicates are handled, and why the memory matters. An agent has enough context to invoke the tool correctly without needing more information.

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 enriches the `text` parameter with concrete examples and explicit exclusions (tool behavior, phone numbers, emails). It does not add much about `category`, but the schema already enumerates the category options and default.

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 and resource: 'Save a durable fact or PREFERENCE... into the workspace Memory'. It gives concrete examples and clearly differentiates from sibling tools like list_memory, forget, and tidy_memory by emphasizing persistence and influence on future ads.

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 clearly says when to use the tool ('For lasting things, not one-off requests') and gives strong negative guidance about what must never be stored. It does not explicitly name alternative tools for one-off or retrieval scenarios, so it stops just short of full alternative routing.

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