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

Annotations already establish readOnly/idempotent/non-destructive, and the description adds material context beyond them: the plan-gating behavior and exact error code (PLAN_REQUIRED), that the document is returned inline rather than as a link, and the universal `attribution` block present in every export including the trailing CSV line.

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 core purpose and then dense with genuinely load-bearing detail; nearly every clause carries information an agent needs (export payloads, attribution, PDF exclusion, plan gate). It is a single heavy paragraph, so mild restructuring would help readability, but there is little waste.

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?

With no output schema, the description carries the return-value burden and does so thoroughly — contents of each export, the attribution block, and the inline (not link) delivery model. Combined with the plan and sibling-routing notes, an agent has everything needed to call it correctly.

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 only 33%, so the description has to compensate, and it does for `type` by describing the payload of each of the five enum values. `corner` is only gestured at ('the solved result at one corner') and the nom/min/max/worst values are left to the schema, and `designId` is undocumented, so it falls just short of full compensation.

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 ('Export a cloud design') and then enumerates exactly what each export type yields, so an agent can distinguish bom_json from design_json from solve_json at a glance. It also explicitly separates itself from siblings open_in_editor (PDFs) and run_derating (derating checks as data).

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 routing: which type to pick, that PDF exports are not available here and the agent should hand the user an open_in_editor URL instead, that derating checks live in run_derating, and that a Pro/Team plan is required (Free refused with PLAN_REQUIRED). This is when-to-use, when-not and alternatives all named.

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