start_capture

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

With no annotations, the description carries the full burden, and it does disclose the key behavioral trait: the operation is asynchronous, background, non-blocking and may run longer than 60s. It also implies the data lands on disk only when stop_capture is called. However, it says nothing about error conditions (e.g. a capture already running), permissions, or what happens to any in-progress capture.

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?

Two compact sentences with zero filler, front-loading the operation and its async nature before the follow-up tool routing. Nothing could be removed without losing meaning.

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 and no annotations, the description supplies the essential context: async execution, expected duration, and the start/status/stop lifecycle. Missing only edge-case behavior for repeated invocation, which would round it out fully.

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 schema accepts zero parameters, so there is no argument semantics to explain; the baseline for a parameterless tool applies. The description correctly adds no redundant parameter talk.

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 ('start a long capture') and immediately adds the defining traits (background, non-blocking, can exceed 60s). It clearly separates itself from stop_capture/get_capture_status by naming them as the follow-up steps, though it does not explicitly contrast with the ambiguous 'capture' sibling.

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?

Provides explicit workflow routing: start here, then use get_capture_status to poll, then stop_capture to finish and persist. This tells the agent when to reach for the neighboring tools. It stops short of stating the condition under which the plain 'capture' sibling should be chosen instead.

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