log_user_preference

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

With no annotations provided, the description must convey behavioral details on its own. It states the tool writes to a 'persistent memory database', which implies a write operation, but it does not disclose whether logging is idempotent, whether duplicate entries are possible, or what the success/error response looks like. For a mutation tool, this is a significant transparency gap.

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 a single clear sentence, front-loaded with the action and scope. It is efficient and free of filler, though it could be improved by adding usage guidance or behavioral notes, but those are separate dimensions. Structure is clean and easy to parse.

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 two-parameter tool with no output schema and no annotations, the description is incomplete. It tells what the tool does but not when to use it (usage context) or what happens on invocation (behavioral guarantees). While the schema covers parameter semantics, the description leaves the agent without guidance on when this tool is appropriate or what results to expect, making it insufficient for reliable selection.

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%, as both category and preference have descriptions in the schema. The description adds loose synonyms (e.g., 'styling taste' for design, 'tech stack choice' for tech_stack) that map to the enum values, but does not provide any new operational meaning beyond what the schema already documents. This meets the baseline for high coverage.

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 ('Logs') and resource ('user preference, styling taste, tech stack choice, or coding habit') and names the destination ('persistent memory database'). This distinguishes it from sibling read tools like get_agent_memory and search_agent_memory, as well as from log_mistake_autopsy, by clarifying what type of information is stored.

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 does not explicitly state when to use this tool versus alternatives. It implies usage for capturing user preferences but gives no contrast with log_mistake_autopsy (for mistakes) or memory-read tools. There is no 'when not to use' guidance or mention of alternative tools to prefer in specific cases.

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