create_device_sniffer

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

With no annotations, the description carries the burden well: it discloses that the capture runs continuously while status='enable', that stopping requires disable/delete, and that there is no packet-count cap. It omits operational context an agent would want for a config mutation on FortiManager — whether an ADOM commit (commit_adom) or install is required for the change to take effect, and what happens if sniffer_id collides with an existing entry.

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 opening sentence front-loads the action and target, and the Args block is justified given zero schema coverage. The parenthetical path strings and backticked object names are somewhat verbose, but the material is substantive rather than 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?

For a 12-parameter mutation with no annotations, the description covers purpose, object identity, parameter formats, and lifecycle. An output schema exists so return values need not be explained (the extra 'Returns' line is harmless). The remaining hole is deployment semantics — commit/install requirements and ID-collision behavior — which matters for a FortiManager write tool.

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 0%, so the description must compensate, and it does: all 12 parameters are documented inline with formats and examples ('1.1.1.1', '2.2.2.0/24', '80', '1-1024', IANA protocol number as string), defaults for capture_ipv6/capture_non_ip/status/vdom, the 0-9999 range for sniffer_id, and auto-assignment semantics when omitted. This adds substantial meaning beyond the bare JSON schema types.

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 ('Create a firewall sniffer definition on a managed device') and pins down exactly which object is created (device-DB firewall.json /firewall/sniffer). It explicitly disambiguates from the same-named FortiManager local diagnostic sniffer, so the agent knows this is a persistent FortiOS config object, not a local capture.

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 for choosing this over the FortiManager local sniffer and clarifies the lifecycle difference ('no packet-count cap or start/stop action... disable or delete it to stop'). It does not however route the agent between this and sibling tools like create_device_on_demand_sniffer or start_packet_capture, so the alternative choice is only partially resolved.

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