Perceived effort (RPE) 1-10, or null to clear it. Partial PUT of summaryDTO.directWorkoutRpe, which Garmin stores TIMES TEN: pass RPE 1-10 (integer), it sends 10-100; null clears it. Garmin itself rejects 150 with a 400 MEASUREMENT_NOT_VALID. Never read-modify-write the whole summaryDTO instead: PUTting its stored start-coordinate pair back is a 400.
| Name | Required | Description | Default |
|---|---|---|---|
| rpe | Yes | ||
| activityId | Yes | Numeric id |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only cover readOnly/destructive/openWorld; the description adds substantial non-obvious behavior: Garmin stores the value times ten, the 10-100 wire range, the server-side 400 `MEASUREMENT_NOT_VALID` rejection at 150, the partial-PUT semantics, and the read-modify-write pitfall that yields a 400. This is exactly the kind of context annotations cannot express.
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-loads the essential constraint (RPE 1-10 or null) and every sentence carries real signal, but 'null clears it' is stated twice, a small redundancy in an otherwise dense, well-ordered description.
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?
No output schema, yet the description covers the error behavior (400 responses) and the mutation semantics an agent needs; with annotations covering the safety profile and the only ambiguous parameter fully explained, nothing needed to call this correctly is absent.
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 only 50% (`rpe` has no schema description), and the description fully compensates: integer 1-10, `null` to clear, and the internal ×10 transformation. `activityId` is covered by the schema as a numeric id, so nothing material is missing.
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 (set) and resource (perceived effort / RPE on an activity), and names the exact underlying field `summaryDTO.directWorkoutRpe`, which cleanly separates it from the many other `set_activity_*` siblings that target different fields (feel, name, description, type).
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?
Clearly states the two modes of use (pass RPE 1-10, or `null` to clear) and explicitly warns against the wrong approach (read-modify-write of the whole `summaryDTO`). It does not route to a sibling alternative, but no obvious sibling competes for this operation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
