Get Preferences

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

With readOnlyHint=true already covering the safety profile, the description adds substantive context beyond annotations: the whitelist constraint, enum-as-name formatting, and the three refusal conditions including the explanation that preferences live in the running application rather than a file. This is genuinely useful behavioral detail.

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 content is front-loaded and dense, but the phrasing is telegraphic and relies on jargon ('whitelisted', 'Pack: settings · lean: no') that is not self-explanatory. The trailing 'Pack · lean' fragment occupies space without clear meaning for an agent.

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?

An output schema exists, so return values need not be spelled out, and the description covers the whitelist scope, value formatting, and failure modes. For a single-optional-parameter read tool this is close to complete, lacking only a cross-reference to the setter sibling.

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% and the `keys` schema already enumerates every whitelisted key, so the baseline is 3. The description reinforces the whitelist boundary and gives one enum example, but adds little syntax or format information the schema does not already carry.

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 identifies the resource (whitelisted `Preferences.*` values) and adds concrete output detail (enum values as names, `read_only` naming Files.* paths), but never states an explicit verb like 'returns' or 'gets' — the read action is only implied by the name/title. It also does not differentiate from the sibling system_preferences_set, which an agent could easily confuse.

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-not conditions via 'Refusals': headless, `capability: "preferences"`, and a key outside the whitelist. That tells an agent when this call will fail, which is meaningful guidance, though it never names system_preferences_set as the counterpart tool or explains when to prefer one over the other.

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