Clear Samsung Health Incremental Import Cache

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

Goes well beyond the annotations: it names the concrete file destroyed, describes the downstream effect on samsung_health_list_records with incremental_cache: true, notes the automatic invalidation path, and documents the explicit_user_intent gate. Annotations already declare destructiveHint/idempotentHint, so this is additive context rather than the sole safety signal; the only unstated piece is what a successful call returns.

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?

Front-loaded with the action and target file, followed by what the cache is, when to use it, and the safety gate — a logical order with no filler. The parenthetical 'requires explicit user intent to wipe local cache' slightly restates the parameter name and could be trimmed.

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, non-read-only maintenance tool with no output schema, the description covers the target, the effect, the trigger conditions, and the safety gate. The only missing element is a note on the return value or confirmation shape, which matters somewhat given there is no output schema.

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 50% (only explicit_user_intent is documented), and the description compensates for the more consequential parameter by explaining it is a safety gate requiring explicit user confirmation to wipe the local cache. The response_format parameter is not addressed in the description, though its enum makes its meaning largely self-evident.

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?

States a specific verb ('clear') plus the exact resource ('incremental import cache'), including the on-disk path ~/.samsung-health-mcp/incremental-cache.json. It also explains what the cache contains (latest parsed timestamp per record category), so an agent understands the object being cleared and can distinguish it from siblings like samsung_health_reimport.

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?

Gives explicit when-to-use guidance: 'Use this when you want to force a full re-parse without changing the export file,' and explains the alternative automatic path (auto-invalidation on export mtime change), which tells the agent when this tool is unnecessary. It does not explicitly contrast with samsung_health_reimport, which is the most likely confusion point among siblings, so it stops short of a full 5.

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