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

Description discloses storage as key-value pair scoped by identifier, different persistence (authenticated vs. anonymous), and pairing with recall/forget. Annotations show idempotentHint=true and destructiveHint=false, which are consistent—no contradiction. Description adds valuable behavioral context beyond 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?

5 sentences, each earning its place: purpose, usage guidance, storage details, scope/persistence, and references to sibling tools. Front-loaded with key action and examples.

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?

Fully covers what the tool does, when to use, what it stores, scope, persistence, and relationships to recall/forget. No missing context for a simple 2-parameter tool without output 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 coverage is 100% with each parameter described (key as memory key, value as any text). Description adds naming conventions (e.g., 'subject_property') and clarifies value can be findings, addresses, preferences, notes—extending meaning beyond 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?

Description starts with 'Save data the agent will need to reuse later' and gives concrete examples (resolved ticker, target address, user preference, research subject). Clearly distinguishes from siblings like 'recall' and 'forget', which are explicitly mentioned.

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?

States 'Use when you discover something worth carrying forward' and provides example scenarios. Implicitly guides when not to use by referencing retrieval (recall) and deletion (forget). Could be more explicit about when not to use, but still effective.

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