start_timerStarts your timer on an item. A timer running elsewhere is stopped first — you only ever have one, across all your workspaces. stopped says which one ended.
| Name | Required | Description | Default |
|---|---|---|---|
| key | Yes | Like APP-123. | |
| note | No | A note on the time entry. |
| Name | Required | Description | Default |
|---|---|---|---|
| key | Yes | The item key. | |
| stopped | No | The timer that was stopped first, in words. Null when none was running. | |
| startedAt | Yes | When it started, in your local time. |
Changes observed during successful MCP inspections.
Output schema / properties / stoppedAdded value: +{
+ "description": "The timer that was stopped first, in words. Null when none was running.",
+ "type": [
+ "string",
+ "null"
+ ]
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), and the description adds real behavioral context beyond them: only one timer exists across all workspaces and starting a new one terminates the previous one, which is a meaningful side effect on other resources. It does not mention auth or rate limits, but for a timer tool that is acceptable.
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, front-loaded with the action and immediately followed by the side effect. The closing 'stopped says which one ended' is somewhat redundant given an output schema exists, but it is brief and reinforces the uniqueness rule.
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?
With annotations, a full output schema, and 100% schema coverage, the description only needs to add behavioral nuance, which it does via the single-timer rule. Nothing an agent needs to call it correctly appears to be missing.
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 100% with only two parameters, so the schema already carries key and note semantics. The phrase 'on an item' loosely maps to key, but the description adds no format or constraint detail beyond the schema's 'Like APP-123' example. Baseline 3 applies.
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 and resource ('Starts your timer on an item') that clearly separates it from stop_timer, timesheet, and log_time. It does not, however, address the potentially confusable sibling start_work, leaving that distinction to inference.
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 implies when to use it (when starting tracked time on an item) and discloses a precondition-like behavior, that any running timer is stopped first. It never names an alternative tool or states when not to use this one, so guidance is only implied.
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.