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

Annotations already indicate write (readOnlyHint false), idempotent (idempotentHint true), and non-destructive (destructiveHint false). The description adds valuable context: memory is scoped by identifier, authenticated users get persistent memory, anonymous sessions retain for 24 hours. This exceeds annotation coverage without contradiction. Slight gap: no mention of overwrite behavior or return value, but idempotent hint implies overwrite.

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 three sentences, front-loaded with the primary purpose. Every sentence earns its place: purpose, usage guidance, and storage/persistence details. No redundancy or filler.

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 tool with rich annotations and 100% schema coverage, the description covers purpose, use cases, persistence, scoping, and sibling relationships. It lacks an output schema, but no return-value explanation is expected for such a straightforward write operation. The description is fully self-contained.

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% with clear descriptions for both key and value, so the baseline is 3. The description adds examples of use ('a resolved ticker, a target address...') that reinforce but do not significantly extend the schema's meaning. The key-value scoping is mentioned but already implied by 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 a clear, specific verb and resource: 'Save data the agent will need to reuse later.' It distinguishes itself from siblings by explicitly pairing with recall and forget, and clarifies cross-session scope. The purpose is unmistakable and well-differentiated.

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 provides explicit guidance on when to use: 'Use when you discover something worth carrying forward' with concrete examples (resolved ticker, target address, user preference). It also explains persistence differences (authenticated vs anonymous) and names complementary tools, making the alternative usage clear.

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