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

Annotations already indicate non-read-only, non-destructive, and idempotent behavior. The description adds valuable context beyond annotations: keys are scoped by agent identifier, persistence differs between authenticated (permanent) and anonymous (24 hours), and it operates as key-value pairs. It does not detail overwrite semantics, but idempotentHint already covers repeatability.

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?

Three sentences, front-loaded with the core purpose. Each sentence adds distinct value: what it does, when to use it, and how it relates to sibling tools. No fluff or redundancy.

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 no output schema, the description covers storage semantics, persistence behavior, and usage context. Combined with schema and annotations, it is fully sufficient for an agent to select and invoke this tool 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 coverage is 100% with descriptions for both key and value. The description goes beyond the schema by providing concrete examples of keys ('a resolved ticker, a target address') and clarifies that value accepts 'any text,' helping the agent understand expected formats and use cases.

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 clearly states the tool's function: 'Save data the agent will need to reuse later.' It uses a specific verb ('save') and resource ('data'), and distinguishes itself from sibling tools like recall and forget by framing it as the write operation in a memory workflow.

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?

Explicit guidance is given: 'Use when you discover something worth carrying forward... so you don't have to look it up again.' It also names alternatives: 'Pair with recall to retrieve later, forget to delete,' making the tool's role in the ecosystem clear.

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