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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, and the description is consistent with that by explicitly saying nothing is published. It adds genuinely useful context beyond the annotations: the OAuth requirement for the downstream publish step and the fact that the output includes a suggested price and photo plan. It does not explain why idempotentHint=false (i.e., that repeated drafts may differ), which is the one behavioral trait an agent would most benefit from knowing.

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?

Four sentences, front-loaded with the core purpose and then the non-publishing constraint, with the worked example earning its place by showing the expected input shape. Slightly dense parentheticals, but no filler.

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?

An output schema exists, so return values need not be described, and the auth/publish boundary is covered. However, for a 10-parameter tool with 20% schema coverage, the description leaves too much of the input surface unexplained for an agent to fill a good draft confidently.

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 20% — just knownIssues and itemCondition carry descriptions — and the prose does not compensate for the other eight. The example mentions year, condition and city, which maps loosely onto three fields, but required fields (brand, model), groupset, frameSize and willShip get no explanation of format or effect on the draft.

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?

The description uses a specific verb and resource ('turn a seller's raw facts into a polished Cyclesite listing draft') and enumerates the produced artifacts: title, description, suggested price, photo plan. It also implicitly separates itself from the publishing siblings by stating 'Does not publish anything', so an agent can route between drafting and publishing without opening either 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?

It establishes the usage context ('sell-side helper', 'useful for previewing what a listing would look like') and states the exclusion that publishing requires a signed-in OAuth account, which is a real gating condition. What it lacks is an explicit pointer to named siblings such as publish_listing or suggest_listing_price, so the agent must infer the handoff.

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