Start recording client HTTP requests

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

Annotations cover safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=true, openWorldHint=true), so the bar is lower, and the description still adds useful context: what is captured (metadata, headers, status codes, timing) and the prerequisite of an active CDP connection. It doesn't say what happens to a previously captured buffer on re-invocation, which is the main remaining gap.

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?

Front-loads the core action, then layers usage, routing, behavior, and prerequisite in clearly ordered sentences. It is on the longer side and the 'Behavior'/'Prerequisite' labels are slightly verbose, but no sentence is wasted given the routing value it provides.

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, no-output-schema tool with annotations present, the description covers purpose, capture scope, prerequisite, and follow-up tools. The one omission is how recording terminates (lol_cdp_network_stop exists as a sibling but is not referenced), leaving the lifecycle slightly incomplete.

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?

Zero parameters and empty input schema, so per the rubric the baseline is 4. There is no parameter surface for the description to clarify or obscure.

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 action (attach via CDP and begin capturing outgoing/incoming HTTP/HTTPS requests) plus the storage destination (in-memory buffer). It is clearly distinguishable from siblings like lol_cdp_network_tail, summary, or body, which are named as downstream consumers rather than competitors.

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 says when to use it (monitor REST traffic, measure endpoint latency, debug failed API calls) and routes to alternatives for other needs: tail/summary for inspection, body for payloads, lol_events_*/lol_wamp_record_* for WebSocket events. This is explicit when-to-use plus when-not-to-use coverage.

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