create_waf_profile

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

With no annotations, the description carries the full burden and does a solid job: it discloses that nested sections are created with FortiManager/FortiOS defaults, which is the key behavioral fact an agent needs to avoid assuming it can configure signatures here. It does not cover permission/locking requirements or idempotency on duplicate names, which is the remaining gap.

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 prose is front-loaded: purpose first, then the important scoping caveat, then args. The Args/Returns/Example blocks are conventional but partly redundant since the input schema and an output schema already exist; the example is still a cheap concrete usage anchor.

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?

An output schema exists, so the Returns block is not strictly needed, but the description still adds the one thing that matters most for this tool: the defaults caveat on nested sections. It is complete enough to call correctly, with the only real omission being whether the target ADOM must be locked before creating.

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 0%, and the description does document all five parameters plus value domains for external and extended_log ('enable'/'disable') that the schema lacks (they are untyped strings with no enum). However, adom, name, and comment get only tautological glosses ('ADOM name', 'Profile name', 'Optional comment'), so it only partially compensates for the coverage gap.

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?

The description leads with a specific verb+resource: 'Create a WAF (Web Application Firewall) profile.' Combined with the sibling set (get_waf_profile, update_waf_profile, list_waf_profiles, delete_waf_profile), the scope of this tool is unambiguous, and the follow-up paragraph clarifies exactly what the created object contains versus what it does not.

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?

It explicitly states when the tool is insufficient: fine-grained control of nested signature/constraint/method/url-access sections is 'out of scope' and must be done via GUI/CLI 'or a follow-up tool once this profile exists.' That is a clear when/when-not statement, though the follow-up tool (update_waf_profile) is never named and no prerequisites (e.g. ADOM locking) are given.

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