Memory Remember

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does well by revealing the duplicate-detection behavior and the `status="duplicate"` return value, which is not visible in the schema. It could go further by noting whether the tool overwrites existing facts or how it handles conflicting facts, but the duplicate behavior is a meaningful disclosure beyond the structured fields.

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: the core action is in the first sentence, followed by clear usage guidance and a behavioral note. Every sentence earns its place, and the duplicate warning is placed at the end where it reinforces the usage rule without cluttering the main purpose.

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 write tool with no annotations, the description covers the essential decision boundary (when to use, when not to use) and a key behavioral outcome (duplicate detection). The output schema exists, so return values need not be explained. It is slightly incomplete in that it doesn't mention whether the fact is upserted or how category/confidence defaults behave, but the schema covers those defaults and the description is otherwise sufficient for correct invocation.

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 all five parameters thoroughly. The description adds a useful example ('prefers uv over pip') and clarifies the intended semantics of 'content' as a durable fact, but it does not need to add much more because the schema is complete. Baseline 3 is appropriate.

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: 'Store one durable fact about the user.' It clearly distinguishes this from siblings like memory_get, memory_search, and memory_remember_conversation by emphasizing durable, user-stated facts rather than transient or conversational details. The scope is precise and immediately actionable.

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 explicitly states when to use the tool ('when the user states a preference, corrects you, or shares context worth carrying into future sessions') and when not to use it ('Do NOT use it for transient details of the current task'). It also warns against re-saving duplicates, which is a clear exclusion that helps an agent avoid redundant calls.

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