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

Annotations already indicate a write operation (readOnlyHint=false, destructiveHint=false, idempotentHint=true). The description adds valuable behavioral context beyond annotations: persistence scoping by user identifier, retention policy (24 hours for anonymous, persistent for authenticated), and key-value storage format. It doesn't mention overwrite behavior, but annotations cover idempotency, so the added context is useful without being exhaustive.

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 sentences, each earning its place: purpose, usage triggers, behavioral details, and companion tools. It is front-loaded with the core function and avoids redundancy or fluff. Every sentence contributes to understanding.

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?

Given the tool's simplicity (2 required params, no output schema, no nested objects), the description covers everything needed: what it does, when to use it, how data is stored (key-value scoped to identifier), persistence rules, and how it relates to recall/forget. It is complete for an agent to select and invoke correctly.

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 covers both parameters fully (100% coverage), so description doesn't need to re-explain them. However, it adds meaningful examples for key naming conventions ('subject_property', 'target_ticker') and clarifies the value type ('any text — findings, addresses, preferences, notes'), which goes beyond the schema's generic descriptions. This adds practical guidance for tool invocation.

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 verb-object structure: 'Save data the agent will need to reuse later' and immediately distinguishes itself from sibling tools by naming recall and forget. It gives concrete examples (resolved ticker, target address, user preference) that make its purpose unmistakable.

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 explicitly states when to use it ('Use when you discover something worth carrying forward...') and provides examples of appropriate use cases. It also references sibling tools ('Pair with recall to retrieve later, forget to delete'), giving clear contextual guidance on how it fits into a workflow.

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