Query local Samsung Health export tables with read-only DuckDB SQL to analyze daily activity, sleep timing, workouts, weight, and trends without altering raw data.
Run a read-only DuckDB query. Main table: daily. Others: hourly_steps, exercise, sleep_sessions, weight, day_tz, day_home.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden; it does state the operation is read-only, which is the single most important safety fact for a SQL tool. However it is silent on row limits, the default limit of 200, timeouts, error behavior on invalid SQL, and whether any statement other than SELECT is rejected.
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?
Two short sentences, zero waste, with the read-only constraint and the main table front-loaded before the supporting table list. Every clause gives the agent information it could not get from the schema.
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?
An output schema exists so return-value explanation is unnecessary, and the table inventory covers the hardest part of using a raw-SQL tool. The remaining gap is the undocumented `limit` parameter and the absence of routing guidance against the specialized siblings.
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 0%, so the description must compensate; it partially does by enumerating the available tables, which is essential semantic context for constructing the `query` argument. It says nothing at all about the `limit` parameter (its default 200, whether it can be raised, or what it does to wrapped queries), leaving half the surface undocumented.
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+resource ('Run a read-only DuckDB query') and immediately names the primary table plus six secondary tables, which tells an agent exactly what domain it is querying. It is distinguishable from the analytics siblings (overview, monthly_trends, trips), though it never explicitly frames itself as the raw-SQL escape hatch.
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?
There is no guidance on when to use raw SQL versus the many purpose-built siblings (overview, sleep_timing, hourly_profile, etc.), and no stated prerequisites, cost, or row-limit warnings. The agent must infer that this is the fallback for questions the specialized tools cannot answer.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.