search_preferences

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds value by mentioning cross-project scope, LLM-distilled nature, and highest-frequency-first ordering. However, it does not explain the return format or behavior when no results are found, which would be helpful given no output schema.

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?

Three short sentences: version identifier, filter options with examples, usage guidance, and ordering behavior. Every sentence adds unique value with no redundancy or fluff. Front-loaded with purpose before parameter details.

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?

The description adequately covers purpose, usage guidance, filtering, and ordering for a simple read-only search. However, it lacks details on the return format (what fields each preference includes) and the effect of omitting the 'category' parameter. Given no output schema, more explicit output description would improve completeness.

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 0%, so the description must compensate. The description explains the 'category' parameter with three example values ('communication', 'workflow', 'formatting'), adding meaning beyond the raw string type. However, it does not explicitly mention the 'top_k' parameter or its role in limiting results, only implying it through 'Highest-frequency first'. This leaves ambiguity for the agent.

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 states the tool searches learned user preferences (cross-project, LLM-distilled) and provides specific filter categories. The verb 'search' and resource 'learned user preferences' are explicit, and it distinguishes from siblings like 'distill_preferences' by focusing on searching existing preferences rather than creating 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 explicitly says 'Use before adopting a tone or workflow the user may have expressed opinions about,' providing clear usage context. However, it does not explicitly state when NOT to use it or compare to alternatives like 'search_decisions' or 'query_graph' from the sibling list.

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