Send a custom RakNet packet

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

Annotations already declare destructive/openWorld/non-idempotent, but the description goes further: it discloses the disconnect/protocol-break risk of malformed payloads or wrong metadata, the approval requirement, the medium cost, that it performs external socket I/O, and that it produces an operation-receipt verifiable with assert-state. That is real behavioral context beyond structured fields.

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 critical 'WRITES LIVE GAME STATE' warning and the core verb before the metadata tags. The trailing phase/cost/idempotency/requires/verify tag block is dense but each token is terse and distinct, though 'On failure: inspect tool-schema...' is generic filler.

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?

No output schema exists, and the description compensates by stating what is produced (operation-receipt) and how to verify it (assert-state), plus prerequisites, approval and failure guidance. For a destructive, open-world socket-writing tool this is complete enough to call correctly.

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 each parameter, setting the baseline at 3. The description only adds the byte-array conversion detail for dataHex and restates the field list; priority/reliability/orderingChannel semantics come entirely from the schema.

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, resource, direction and mechanism: sends a custom OUTGOING low-level RakNet packet via raknet.send with payload/priority/reliability/ordering channel. The 'OUTGOING raw packet' framing clearly separates it from observation siblings like packet-spy or block-packets without opening 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 preconditions (requires the `raknet` library, active-client, explicit-mutation-approval) and a use constraint ('only send payloads you understand'). However, it never names a higher-level alternative such as fire-remote for normal remote traffic, so the agent gets context but no explicit routing away from this low-level tool.

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