get_firmware_upgrade_report

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

With no annotations, the description carries the disclosure burden and does reasonably well: it frames this as a reporting/read operation, states the profile must pre-exist and is not auto-generated by this module, and gives the return shape including status/report/message and the failure path. It does not mention permissions or how long a run must exist before a report is available, which would complete the picture for a mutation-adjacent toolchain.

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?

Purpose is front-loaded in the first sentence, but the middle paragraph spends roughly half its length on meta-commentary about a How-To Guide entry marked TBD and why no history tool exists. That justification has some value for disambiguation, yet it is verbose and could be compressed to one clause.

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?

Purpose, prerequisites, all three parameters, and return keys are covered, so an agent can invoke it correctly. An output schema exists, making the detailed Returns block somewhat redundant. The remaining gap is behavioral rather than informational: nothing about read-only semantics or auth/permission expectations for an unannotated 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 description coverage is 0%, so the description must compensate, and it does: an Args block defines device, profile_name, and adom, including the adom default resolution (DEFAULT_ADOM env var, else 'root'). The profile_name origin constraint is substantive semantic information absent from the schema. 'device: Managed device name' is the thinnest entry but adequate.

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 ('Get the firmware upgrade report') scoped to a device under a named profile, and explicitly separates it from the firmware workflow siblings (upgrade_device_firmware, get_firmware_upgrade_path, list_firmware_images) by describing the output as per-step upgrade results for a tracked run. The note about the hypothetical 'upgrade history' endpoint further pins down what this tool is and is 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?

Explains the precondition that profile_name must already be a firmware upgrade profile known to FortiManager (GUI wizard or the Firmware Template key returned by an ext-style upgrade), which tells the agent when this call can succeed. It also resolves the alternative — the How-To Guide's 'get upgrade history' question is unconfirmed and maps to this same endpoint, so there is no sibling to route to. No explicit when-not-to-use beyond that.

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