start_context_watcher

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

With no annotations, the description discloses the key side effect of opening a persistent terminal, which is an important behavior. It also explains tracking behavior and handover recommendation. However, it doesn't mention configurable options like noTerminal, which changes the behavioral profile, though those are covered in the schema.

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?

The description is two sentences with no wasted words. It front-loads the main action ('Open a persistent terminal') and efficiently states what the tool tracks.

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?

The description covers the tool's purpose, side effect, and tracking scope. It is adequate for a tool with a complete schema, though it lacks explicit usage guidance that would make it more complete.

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?

The input schema provides complete descriptions for all three parameters (sessionId, noTerminal, autoCloseTerminal), so the description does not need to add param details. It adds no extra meaning beyond what the schema already explains.

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 tool's action ('Open a persistent terminal') and its purpose ('real-time token usage'). It also specifies what it tracks ('every Cerebro tool call with estimated tokens and handover recommendation'), distinguishing it from sibling tools like stop_context_watcher and get_context_health.

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 the tool is for watching token usage in real-time, but does not explicitly state when to use it over alternatives like get_context_health or prepare_handover. No exclusions or conditions are provided.

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