prefer

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

No annotations are provided, so the description carries full behavioral disclosure. It states 'Highest trust level,' 'Persists across sessions,' and 'surfaced in every brief(),' which are meaningful behavioral traits beyond just the write action. This is substantial transparency for a simple recording tool.

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 starts with the primary use case, followed by clear examples and practical scoping tips. Every sentence carries useful information, though the prose is slightly run-on and could be structured more cleanly.

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 2-parameter tool, the core behavior, persistence, and scoping are covered. However, the large set of sibling memory tools (learn, conventions, gotchas, recall) makes it unclear when to choose 'prefer' over these alternatives. The description would be more complete if it explicitly distinguished itself from those tools.

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 baseline is 3. The description reinforces that 'rule' is required and gives examples, but the lobe scoping and rule description are already present in the input schema. The description adds little beyond illustrative JSON examples.

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 clearly identifies the tool's purpose: when the user corrects you or states how they want things done, record it here. It names the resource (preferences/rules) and includes concrete examples. However, it does not explicitly differentiate from sibling memory tools like 'learn' or 'conventions', so it gets a 4 rather than 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 description provides an explicit trigger condition ('When the user corrects you or states how they want things done') and scoping instructions ('Omit lobe for global preferences; add lobe to scope to one project'). It does not mention exclusions or alternative tools, but the context is clear enough for basic use.

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