network/arp

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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description still adds substantial behavioral context beyond them: the cache's staleness limitation, IPv6 exclusion, the namespace scoping, and the null-vs-[] return quirk.

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-loaded with the core purpose, then scope, limitations, alternatives, and return shape in a tight sequence. Every sentence carries distinct information; none is padding.

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 output schema, the description fully specifies the return contract – always JSON, an array of objects with named fields, and null (not []) when empty. Combined with the cache caveats, nothing an agent needs to call and interpret this tool 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% and the schema already documents `interface` as the exact interface name with omission meaning all. The description's elaboration ('exact device name (eth0); omit it for all') largely restates the schema, so 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+resource (shows the kernel's ARP cache), its exact data source (/proc/net/arp), and its scope (daemon's network namespace). It explicitly distinguishes itself from network/connections and network/ping, so an agent can select it without opening a 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?

Names the alternatives explicitly with conditions: network/connections for sockets/connections and network/ping for reachability. It also tells the agent when NOT to expect results (cache, not a scan; IPv6 excluded), leaving nothing to inference.

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