Spy on outgoing RakNet packets

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

Far exceeds the annotations: it discloses that start installs a hook, fetch is non-destructive to the buffer, stop removes the hook and CLEARS the buffer, requires the `raknet` library, and that interception is risky and can disconnect/flag the client. This is exactly the kind of consequence-level detail the destructiveHint annotation cannot convey. The only nuance is that 'start ... (idempotent)' sits in mild tension with tool-level idempotentHint=false, but the qualifier is action-specific and the overall non-idempotent reading holds.

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 most important fact ('WRITES LIVE GAME STATE') and stays dense, but the trailing metadata boilerplate (Signature, Phase, Capabilities, Produces, Verify, Safety) partially duplicates the schema and annotations. Efficient overall, with a little redundancy.

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 4-parameter mutating tool with no output schema, it covers everything an agent needs: the three actions and their side effects, buffer-clearing behavior, the returned packet fields, the library dependency, and the risk warning. Nothing material to correct invocation is missing.

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 description coverage is 100%, so the schema already documents action, limit, previewBytes, and threadContext. The description's signature block largely restates the schema and adds no format, default, or constraint detail beyond it, so the baseline 3 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: installs a RakNet send hook and captures every OUTGOING low-level packet, enumerating exactly what is recorded (Size, Priority, Reliability, OrderingChannel, hex preview). This cleanly distinguishes it from higher-level siblings like get-remote-spy-logs, trace-remote-traffic, send-packet, and block-packets without needing to open any schema.

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 context: 'RakNet only exposes outgoing traffic' scopes what it can see, and the WARNING plus 'stop when done' tells the agent the right lifecycle. However it never names an alternative tool (e.g. remote-level spies) or an explicit when-not condition, so routing between it and its siblings is left partly to inference.

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