pause_observation

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

The description says the tool will 'invalidate pending drafts,' which is a destructive/canceling effect on pending data, yet the annotations declare destructiveHint=false. This directly contradicts the annotation and could mislead an agent about the tool's safety profile.

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 concise, information-dense sentences. The first states the core action and side effect; the second states the restart consequence. There is no filler or redundant repetition of the schema.

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?

For a zero-parameter tool with no output schema, the description covers the action, the side effect, and the restart implication. It is largely sufficient, though it could explicitly name the restart tool or clarify whether a successful pause returns confirmation.

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?

There are zero parameters, so the schema requires no additional documentation. The description still adds useful context by clarifying that the operation targets the 'current session' implicitly rather than through arguments.

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 states a specific action and effect: 'Pause the current session and invalidate pending drafts.' It clearly identifies the resource (current session) and the behavior, distinguishing it from sibling tools like start_observation and poll_changes.

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 gives clear context for when to use the tool: when the current session needs to be paused. It also implications about restart behavior ('Restart creates a new baseline'), which helps an agent understand the consequence. However, it does not explicitly name alternatives or state when not to use it.

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