Start Task

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

Beyond annotations (which show idempotentHint=true), the description adds behavioral context: it records start time, transitions state, and enables file writes via the hook system. No contradiction with annotations.

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 with zero wasted words. Action verb and resource are front-loaded. Every sentence adds essential information.

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?

Given the annotations, sibling tools, and single parameter, the description fully explains when to use, what it does, and behavioral consequences. No output schema needed as return is likely a simple success indicator.

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 has 0% parameter description coverage, but the single parameter task_id is a UUID whose purpose is obvious from context. Description does not add explicit parameter documentation, but the clarity of the tool's purpose compensates somewhat.

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?

The description clearly states the action ('Mark a task as in_progress and record start time') and the resource ('task'). It also explains the state machine transition (pending → in_progress), which differentiates it from siblings like cph_task_complete and cph_task_cancel.

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?

Explicitly states 'CALL THIS BEFORE writing any code or making any changes for this task' and explains why (hook system requires in_progress task for file writes). Also notes the only valid state transition from this tool.

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