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

Annotations already declare readOnlyHint=true, so the description doesn't need to restate that. It adds valuable context: the scope (account-wide, not per-agent) and the empty-state return (a note saying so). This goes beyond structured fields and helps the agent predict behavior.

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, no fluff. The purpose is stated first, then usage guidance, then empty behavior. Every sentence adds information—nothing is repeated or redundant.

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 getter with no parameters and no output schema, this is complete. It explains what it returns, its scope, when to use it, and the empty-case behavior. An agent can call it correctly without any additional clarification.

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 tool has zero parameters and schema coverage is 100% (empty object), so the baseline is 4. The description adds meaning by explaining what the memory contains, which is directly useful for deciding whether to call it, even though there are no parameters to document.

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 reads the user's saved memory, listing exactly what it contains (durable facts, preferences, context). It distinguishes itself from per-agent memory by explicitly noting it's account-wide. This is a specific verb+resource with enough detail to tell it apart from siblings like save_memory or append_learning.

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 gives a clear when-to-use: before asking the user to repeat something, to ground the reply in known facts. It also notes the empty-state behavior. It doesn't explicitly mention alternatives (e.g., search_chat_history for recent context), but for a zero-parameter getter this is sufficient guidance.

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