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

Annotations already mark this as a non-read-only, non-idempotent write, and the description adds meaningful context: memories persist across sessions, the free beta has a bounded per-caller/workspace pool, no API key is required, and secrets/logs are prohibited. This exceeds what the structured annotations convey.

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 efficiently front-loaded with purpose, followed by resource and policy context, and includes a concrete example in four short sentences. Every sentence adds value and there is no padding.

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 one-required-parameter write tool, the description covers purpose, appropriate content, persistence behavior, resource bounds, auth requirements, and exclusions. An output schema exists, so return values do not need to be described.

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 fully documents content, kind, and project. The description adds an example using content but does not materially enrich the parameter semantics beyond the schema, so baseline 3 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 uses a specific verb and resource: 'Persist a durable memory' and enumerates concrete use cases like architecture decisions, preferences, bug fixes, and discoveries. Although siblings are not named, the store operation is clearly distinct from forget/recall, eliminating ambiguity.

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 explicit when-to-use criteria via the listed memory categories and a clear when-not-to-use rule: 'Do not store secrets or raw logs.' It does not explicitly compare against the sibling tools (forget/recall), but context makes the intended usage clear.

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