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

Annotations provide readOnlyHint=false, idempotentHint=true, and destructiveHint=false. The description adds extra behavioral context by explaining 'Stored as a key-value pair scoped by your identifier' and that 'Authenticated users get persistent memory; anonymous sessions retain memory for 24 hours.' This goes beyond the schema and annotations, giving the agent essential information about scoping and persistence.

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 around 60 words and contains no fluff. Sentences are front-loaded with the core purpose, followed by usage triggers, then behavioral details, and finally sibling links. Every sentence earns its place without 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 storage tool, this description covers everything an agent needs: what it does, when to use it, how data is stored and scoped, persistence rules, and how to retrieve/delete it later. The absence of an output schema is acceptable because the operation is a save, and the description implies the effect without needing to enumerate return values.

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?

The input schema already has 100% coverage with descriptions for 'key' and 'value'. The description reinforces the relationship between the two by calling it a 'key-value pair' and adds the scoping behavior ('scoped by your identifier'), which adds meaning beyond the schema. The examples in the schema further clarify parameter usage.

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 — across this conversation or across sessions.' It uses a specific verb ('Save'), names the resource (key-value data), and distinguishes itself from its siblings (recall, forget) by mentioning pairing and retrieval.

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 when-to-use guidance: 'Use when you discover something worth carrying forward (a resolved ticker, a target address, a user preference, a research subject).' It also differentiates between authenticated and anonymous sessions, clarifying persistence expectations. It explicitly references siblings with 'Pair with recall to retrieve later, forget to delete.'

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