update_device_sslvpn_web_portal

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

No annotations are provided, so the description carries the burden, and it does disclose real behavior: the target object must pre-exist, and only supplied fields are modified (partial-update semantics), plus the vdom default of 'root'. Gaps remain for a mutation tool — nothing about ADOM lock requirements (lock_adom/unlock_adom exist in the toolset) or whether the change is staged in the ADOM and needs a commit/install to reach the device.

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 pre-existence constraint and partial-update rule before the Args list, which is the right ordering. The parameter block is justified by the empty schema descriptions, though the 'Returns: Update result' line is near-wasted space given an output schema exists.

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 9-parameter mutation tool with no annotations, the description covers preconditions, partial-update behavior and every argument, and the output schema relieves it of explaining return values. The one material omission is lifecycle: an agent cannot tell from this whether the update takes effect on the device immediately or requires a subsequent install/commit.

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% with 9 parameters, so the Args block is doing essential work: it supplies the accepted values 'disable'/'enable' for tunnel_mode, split_tunneling and web_mode where the schema declares only an unrestricted string, explains that ip_pools takes firewall address/address-group names, and documents the vdom default. This adds meaning well beyond the bare JSON 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 and a highly specific resource ('Update an SSL-VPN web portal in a device's device DB'), which separates it from the sibling update_device_sslvpn_settings (global settings) and from get_device_sslvpn_web_portal. The opening sentence alone lets an agent pick correctly without opening the 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?

Explicit when-to-use ('The portal itself must already exist in the device DB... this tool only updates an existing entry') and an implicit when-not (creation must happen via FortiOS CLI/GUI or a prior install). It does not name the companion read tool or point to update_device_sslvpn_settings for non-portal settings, so routing is clear but not fully enumerated.

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