distill_preferences

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

Description reveals persistence to a specific database, clearing of capture file, version info, and degradation path. This adds significant behavioral context beyond the minimal annotations (readOnlyHint=false, destructiveHint=false).

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 sentences, front-loaded with purpose, then usage, then fallback. No redundant information; every sentence adds value.

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 simplicity (one boolean parameter, no output schema), the description covers when to call, what it does, side effects, and fallback. Minor gap: no mention of return value or error conditions, but adequate for the complexity.

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 has 0% coverage and only one boolean parameter (dry_run). Description explains the effect of dry_run=false but does not explicitly describe the default behavior (dry_run=true). Partially compensates for the schema gap but leaves ambiguity.

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?

Description clearly states the tool distills captured user prompts into durable preferences, specifying verb, resource, and mechanism (via host LLM). It distinguishes from siblings by its unique purpose of cross-project memory creation.

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?

Explicitly instructs to call at session end when the Stop-hook fires, and specifies conditions for persistence (dry_run=false). Includes fallback behavior for unsupported sampling, but could be more specific about when not to use.

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