Trace remote traffic

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

Annotations already declare readOnlyHint=false and destructiveHint=true, and the description goes well beyond them: it warns that start WRITES LIVE GAME STATE, notes the buffer is shared and bounded, explains that stop only closes the view (captures persist), and flags that starting another engine kills the previous spy. It also states prerequisites (active-client, explicit-mutation-approval) and a verification path (assert-state).

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 critical warning ('WRITES LIVE GAME STATE') is front-loaded and the lifecycle is described in tight clauses. The trailing metadata block (Phase/cost/idempotency/Requires/Produces/Verify/Safety) is somewhat boilerplate-heavy, but each line carries actionable content.

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 stateful, mutating, multi-action tool with no output schema, the description covers lifecycle, shared-state hazards, prerequisites, and verification. It does not describe the shape of a fetch result, but with a bounded-snapshot contract stated, that gap is minor.

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?

Schema coverage is 100%, so baseline is 3, but the description adds real semantic value: 'Direction is selected on start' tells the agent that direction is only meaningful on start, not fetch/stop, and the shared-buffer note explains what limit bounds. The engine conflict rule is restated from the schema but reinforced.

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 ('trace remote traffic'), and unpacks the three actions (start/fetch/stop) so their distinct purposes are visible. The 'shares the bounded buffer with all spy tools' clause distinguishes it from sibling readers like get-remote-spy-logs.

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?

Gives clear per-action guidance: start opens the view and selects direction, fetch reads retained captures since start, stop closes only the view. It implies the spy-tool family relationship but never explicitly names an alternative tool to use instead when a different need arises, so it stops short of full when/when-not routing.

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