Skip to main content
Glama

Start the timer

start_timer

Starts a timer on the project_task_id of a project of list_projects, today in the time zone of the workspace. A timer that runs already is refused (timer_running): stop it first.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "project_task_id": "<project_task_id>"
    },
    "name": "start_timer"
  }
}

Input Schema

NameRequiredDescriptionDefault
notesNo
project_idNoThe project of the task, when the client chose it: a project task of another project is `other_project`
project_task_idYes

Output Schema

NameRequiredDescriptionDefault
timerYesThe timer of the member of the token, or `null`
time_entryNo`billable`, `currency`, `hourly_rate`, `amount`, `invoice_id` and `invoice_number` are only for a role that sees amounts, and `cost_rate`, `cost_currency` and `cost` only for a role that sees costs.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare this is a non-read-only, non-idempotent, non-destructive local mutation, so the safety profile is covered. The description usefully adds the failure mode (`timer_running` refusal) and the implicit date/time-zone scoping, but says nothing about what a second call does after a stop, or any permission requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with the action and constraint, with no filler. The phrasing 'the `project_task_id` of a project of list_projects' is slightly convoluted but dense with meaning rather than padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A single-required-parameter mutation with an output schema and full annotations needs modest description, and this supplies the key behavioral traits: task scoping, today/workspace-timezone semantics, and the running-timer refusal. Only the `notes` parameter and the paused-timer interaction are left uncovered.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With only 33% schema description coverage, the description must compensate, and it partly does: it defines project_task_id as a task belonging to a project obtainable via list_projects. However, `notes` is entirely unaddressed and the project_id cross-project constraint (`other_project`) lives only in the schema, leaving a real gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: starts a timer on a given project_task_id, scoped to today in the workspace time zone. This is far beyond restating the name, though it never explicitly distinguishes itself from resume_timer or create_time_entry as alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a concrete precondition: if a timer is already running the call is refused with `timer_running`, and the agent must stop it first — implicitly pointing at stop_timer. It does not clarify when to start a fresh timer versus resuming a paused one, so the coverage of alternatives is partial.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources