Set what private values may be shown in ASSIST mode

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

The description goes well beyond the annotations, explaining that the tool records a decision, that personal data is masked by default, that secrets are never shown, that identity='ask' resets the earlier question, and that the tool returns the resulting state. These are valuable behavioral details not present in readOnlyHint, idempotentHint, or destructiveHint.

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, followed by necessary parameter semantics and behavioral edge cases. Every sentence contributes useful information; there is no filler or 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?

Given the tool's moderate complexity, the presence of an output schema, and strong annotations, this description covers the when, what, parameter meanings, privacy defaults, reset behavior, and return value. Nothing critical is missing for an agent to invoke it correctly.

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?

Even though schema coverage is 100%, the description adds real meaning to the parameters: it defines what 'identity' and 'numbers' concretely cover (names, addresses, emails, phones; account/card/id/SSN numbers and DOB), notes the masked default, and explains the special 'ask' reset value. This is significant added value beyond the enum patterns.

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 opens with a specific verb and resource: 'Record the user's decision on what this ASSIST session may show in clear.' This clearly distinguishes the tool from LLM execution, delegation, artifact, and mode-setting siblings, even without naming them.

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 an explicit usage condition: use this when the user has stated a privacy decision in conversation; otherwise the server asks the user itself. It also explains the reset behavior for identity='ask'. It does not explicitly contrast with sibling tools, but the context is clear enough for an agent to select it.

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