Auto Save

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

With no annotations, the description carries the burden of disclosing behavior. It does so by specifying that the save should be silent, proactive, and not announced unless asked. This is meaningful behavioral context beyond the generic 'save' action, though it does not detail storage semantics such as deduplication or overwrite behavior.

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 concise sentences with no redundant phrasing. The core behavior and trigger conditions are front-loaded, and the instruction about not announcing is placed exactly where it matters.

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 one-parameter tool, the description provides sufficient guidance on when and how to invoke it. It gives trigger conditions, scope of content, and interaction guidance. It does not explain what response to expect or how it compares to closely related memory siblings, but the tool's simplicity limits the impact of that gap.

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?

The schema coverage is 100% and describes 'fact' as 'The fact to remember.' The description adds meaning by specifying what counts as worth remembering: preferences, facts, corrections, and project state, and clarifies that the fact should be about the user and long-term.

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 the verb 'save' and the resource: information about the user worth remembering long-term. It also differentiates this tool from siblings by emphasizing 'silently' and 'proactively during conversations,' which distinguishes it from a manual save_memory operation.

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 explicit trigger conditions: call when the user reveals preferences, facts, corrections, or project state during conversations. It also says not to announce the action unless asked, but it does not explicitly state when to prefer save_memory or update_memory instead, so it lacks full alternative discrimination.

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