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

Annotations already declare readOnlyHint=false, openWorldHint=true, destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context: the action defaults (non-empty content infers store, otherwise recall), the 2 MESH/call cost, and the scoped/private nature of the memory. It doesn't detail what happens on overwrite or deletion, but the annotations plus the action-default disclosure are solid.

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 compact and front-loaded with the core purpose, then gives the action syntax, then the use case, then the sibling contrast, then cost. Every sentence earns its place. Slight redundancy with the schema's action enum, but the inference behavior is worth stating.

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 tool with a rich schema (100% coverage) and annotations covering safety, the description is nearly complete. It explains the action inference, the cost, and the relationship to agent-brain. The only gap is that it doesn't describe the return format of recall results, but with no output schema and the schema already covering inputs, this is a minor omission.

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 description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds value by explaining the action inference behavior (non-empty content/remember/text infers store, otherwise recall) and the cost, which are not in the schema. It doesn't repeat the schema's parameter details, which is appropriate.

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 states a specific verb-resource pair ('Store or recall private, scoped memory') and immediately distinguishes itself from the sibling agent-brain by noting that agent-brain is the reasoning layer that reads/writes memory in the loop. This makes the tool's role clear and differentiates it from its closest sibling.

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?

The description gives explicit usage context: 'Good for continuity across sessions' and contrasts with agent-brain as the reasoning layer. It doesn't explicitly say when NOT to use it or name alternatives beyond agent-brain, but the session-continuity context plus the sibling contrast provides clear guidance.

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