create_dlp_profile

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

No annotations are provided, so the description carries the full burden. It does disclose a meaningful behavioral trait beyond the signature — the created profile is empty and rules must be added elsewhere — plus the return-key shape. However, it says nothing about required permissions, ADOM lock prerequisites, idempotency or duplicate-name behavior, and whether the change needs a commit_adom to take effect, all of which matter for a create mutation on FortiManager.

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 purpose and the key scope caveat in the first two paragraphs, then structured Args/Returns/Example. The Example block largely restates the Args list and adds little, and the Returns block duplicates a structured output schema — mild redundancy rather than bloat.

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 six-parameter create mutation with no annotations, the definition covers purpose, the empty-ruleset consequence, all parameter values, and error/status signaling (reinforced by an output schema). The one consequential omission is the FortiManager workflow prerequisite — locking the ADOM and committing after creation — which an agent could easily get wrong.

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 there are no enums in the schema, yet the description documents every one of the six parameters, including the constrained value sets the agent could not otherwise infer (feature_set = "flow"|"proxy", dlp_log / extended_log = "enable"|"disable") and notes comment is optional. This is exactly the compensation a low-coverage schema needs.

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?

Specific verb + resource ("Create a DLP profile") that is trivially separable from the update_dlp_profile / delete_dlp_profile / get_dlp_profile / list_dlp_profiles siblings. It also adds a real scope nuance — the profile is created empty, with no rules — which changes what the agent should expect to do next. It does not name the sibling tools explicitly, so it stops just short of 5.

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?

Clearly states when this tool is *not* sufficient (rule management is out of scope) and redirects to the FortiManager GUI/CLI or a follow-up tool. What's missing is the positive-side routing: nothing says to use update_dlp_profile for later modification, or that ADOM should be locked first in FortiManager workflows.

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