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

The annotations already indicate this is a non-read-only, non-destructive operation. The description adds useful behavioral context: the memory is 'long-term' and 'about the household,' and storing is discouraged for trivial or transient info. It also advises recalling first to avoid duplicates, which hints at idempotency considerations. It does not describe response behavior, but an output schema exists, so that is covered elsewhere. No contradiction with 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 two sentences, front-loaded with the core purpose. It wastes no words and packs usage guidance, scope, and a pre-step into a compact form. Every sentence earns its place.

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?

This is a relatively simple create tool with 4 parameters, full schema descriptions, and an output schema. The description adds context about when to use (sparingly, durable info) and the recall-first step. It doesn't explicitly explain return values or error handling, but the output schema covers that. It is complete enough for an agent to select and invoke correctly, though a small gap remains around duplicate behavior.

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. The description adds semantics beyond the schema by explaining what kind of content belongs in the memory (durable preferences, routines, constraints, insights) and that it is household-scoped. This helps disambiguate how to fill the 'content' and 'description' fields even though the schema already documents each parameter well.

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 begins with a specific verb+resource: 'Store a long-term memory about the household.' It clearly distinguishes from sibling tools like recall_memory, forget_memory, and update_memory by focusing on the creation of a new memory. It also enumerates the types of content to store (durable preferences, routines, constraints, insights), which sharpens the purpose.

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 explicit usage guidance: 'Use sparingly for durable preferences, routines, constraints, or insights worth recalling in a future conversation.' It also gives a concrete pre-condition: 'Recall first to avoid duplicates,' which implies checking existing memories before storing and indirectly points to the recall_memory sibling. This covers when to use and how to avoid misuse.

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