audit_admin_access

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

With no annotations, the description carries the full burden and does so well: it declares the operation read-only, discloses a genuine side effect (the hash check reads a config backup, which the FortiGate logs as a config download), and describes the return shape (findings graded critical/warn/info with a suggested fix). These are behavioral traits beyond any structured field.

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 scope, followed by return shape, then the side-effect caveat with its opt-out. It is dense and long, but every sentence carries distinct information (checks, return format, side effect) rather than padding, so the length is earned by the tool's breadth.

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, so the description supplies the return semantics (graded findings with suggested fixes). Both parameters are accounted for (vdom via schema, check_hashes via schema plus description detail), and the one non-obvious behavioral caveat is disclosed. Nothing needed to invoke it correctly 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 coverage is 100%, so the schema already documents both parameters (baseline 3). The description adds real semantic value beyond the schema by explaining the why and consequence of check_hashes (it triggers a logged config download) that the raw schema does not convey. The vdom parameter is left to 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 ('Read-only audit of how the FortiGate can be administered') and then enumerates the exact checks (trusted hosts/MFA, default admin, API keys, WAN admin access, local-in policies, legacy SHA-256 hashes). The scope is clearly admin-access focused, distinguishing it from audit_hardening and audit_policy_protection, which an agent can infer even though they aren't named.

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?

Provides usage guidance for one parameter (set check_hashes=false to avoid the logged config download) but never says when to choose this audit over the sibling audits (audit_hardening, audit_policy_protection). Usage context is implied by the enumerated checks rather than explicitly framed as when/when-not.

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