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

Annotations already declare readOnlyHint=true and openWorldHint=false; the description reinforces this by explicitly saying nothing is sent or ordered and by naming the two outputs (request document plus ready-to-send email). That return-value disclosure is genuine added context beyond the annotations, though permission or rate-limit behavior is not mentioned.

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?

Two short sentences with zero filler: the capability and its three modes come first, then the output and the safety constraint. Every clause earns its place and nothing is repeated from the schema.

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?

The description covers the purpose, the outputs, and the no-side-effect guarantee, which is adequate for a read-only draft tool with no output schema. It falls short on the seven unlabeled parameters — an agent must guess at contact and shipping field semantics — which is a meaningful gap for a request-building 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% across 7 parameters, so the description carries the full burden and only partly delivers: the 'buy listed parts, price unlisted ones, or make custom versions' phrasing loosely maps to the request enum values buy/quote/custom, but the mapping is never made explicit. company, needed_by, contact_name, contact_email, ship_to_country, notes, and qty remain completely undocumented in both schema and description.

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 concrete verb and resource ('Build a request for Maglev to buy listed parts, price unlisted ones, or make custom versions') and enumerates the three request modes, so an agent knows exactly what it produces. It partially differentiates from siblings like place_order by stating that nothing is ordered, but it never names those siblings explicitly.

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?

The closing sentence gives a real workflow rule — draft first, show the human, nothing is sent — which implies this is the pre-order step. However, it never names the natural alternatives (place_order, preview_order, get_quotes) or states when to pick this tool over them, so the routing is only implied.

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