Remember in XMemo

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

Beyond the annotations (readOnlyHint=false, idempotentHint=false), the description discloses useful behavioral details: 'Existing Projects paths attach automatically' and that create_project 'may create a missing project only when explicitly enabled.' These are not present in the annotations and add meaningful context for the agent. However, it does not cover other behavioral aspects like deduplication or mutation details, but the bar is lowered given the annotations.

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 four short sentences, purpose-first, with no filler. Every sentence adds value: the main purpose, a behavioral note, a compatibility caveat, and explicit alternative routing. It is concise and well-structured.

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?

With 20 parameters and full schema coverage plus an output schema, the description does not need to enumerate parameters. It provides the essential context: durable vs. transient, auto-attachment behavior, and sibling tool alternatives. It could mention the default dedupe behavior or that it can also update existing memories, but the coverage is sufficient for a tool with a rich schema.

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 baseline is 3. The description adds a small amount of parameter behavior by explaining the create_project compatibility input's gating, but it mostly restates what the schema already says. No additional syntax or format details are given for required parameters like content or path 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 opens with 'Save durable information for future recall'—a specific verb and resource—and explicitly contrasts with transient chat. It also distinguishes from sibling tools by directing financial records to add_expense and actionable work to create_memory_todo, clarifying the tool's scope.

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 when-to-use guidance ('Save durable information for future recall') and when-not-to-use guidance ('skip transient chat', 'Use add_expense for financial records and create_memory_todo for actionable work'). It also notes the create_project compatibility input should only be enabled when explicitly requested, providing a clear usage boundary.

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