Stop recording client HTTP requests

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

Adds behavior beyond the annotations by naming what is lost ('Discards in-memory network buffers') and confirming safety when already stopped. The idempotency claim duplicates idempotentHint and destructiveHint already signals mutation, but the buffer-discard detail is genuinely useful context.

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 tight sentences with the action front-loaded, followed by when-to-use and behavior. No filler or repetition.

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?

With no parameters, no output schema and annotations covering the safety profile, the description gives the agent enough to call it correctly. The one missing piece is a warning that captured data must be retrieved (via tail/body/export) before calling this, since buffers are discarded.

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 tool takes zero parameters, so there is nothing for the description to clarify beyond what the empty schema shows. Baseline 4 applies.

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: 'terminate the network traffic recording session' and 'Detach from the League Client renderer'. This is clearly distinguishable from the sibling start/tail/body tools in the cdp_network family.

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 gates use on completion: 'Use this tool when network analysis is complete to release memory and close the CDP monitoring session.' No exclusions or sibling alternatives are named, so it stops short of a 5 — notably it never tells the agent to export or tail captured data before stopping, even though the buffers are discarded.

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