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

The description adds a real behavioral guarantee not present in the annotations: the note is 'never published', which is meaningful privacy context for a non-read-only write tool. However, it does not disclose overwrite semantics for a repeated key, storage retention, or how notes surface in future sessions — gaps that matter given idempotentHint=false.

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?

Two short, front-loaded sentences with the key constraint ('never published, no secrets') placed before the example. The inline example earns its place by showing the key prefix, though it is somewhat redundant with the schema.

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 full schema coverage and no output schema, the description covers purpose and privacy adequately. It omits what happens on repeated keys and how the note is consumed in the next session, which leaves the agent's mental model of the tool incomplete.

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%, so the schema already documents both key and text, and the description's example largely restates the same information. Baseline 3 is appropriate; the example adds a slight concrete flavor but no format or constraint detail beyond the schema.

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?

States a specific verb and resource ('Save a private note') and clarifies the intended consumer ('for your next session'), which immediately tells the agent this is cross-session memory rather than a task log. It does not explicitly distinguish itself from similar siblings like log_task_plan or log_task_outcome, so it stops short of a 5.

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 phrase 'for your next session' implies when to use it (persisting information across sessions), but there is no explicit when-to-use/when-not guidance and no named alternative among the many sibling logging tools. It also does not say how notes are later retrieved, leaving the workflow half-specified.

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