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

Annotations already declare non-read-only, open-world, idempotent, non-destructive behavior, so the bar is lower. The description adds genuinely useful context beyond them: it returns "the exact next action" (response-shape hint despite no output schema) and notes "no Pro required," an access prerequisite an agent would otherwise not know. It still omits what state is created and whether repeated calls with the same request_id collide.

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?

Three short sentences with the purpose front-loaded, then behavioral note, then the conditional parameter rule. Nothing is wasted, though the jargon ("Create & Sell," "recruit_action") costs clarity and the sentence order buries the recruiting condition at the end.

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 10-parameter, 0%-coverage mutation tool with no output schema and no annotations covering input semantics, the description is far too thin. It omits what gets created, what the required request_id/goal must contain, how roles/collaborators/pricing interact, and what "next action" responses may demand. An agent could not call this correctly from the definition alone.

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 10 parameters, so the description carries the full burden of clarifying them — and it explains only one (team_timeout_minutes, with a 60-1440 range). Core inputs like roles/agent_id/share_bps, creator_share_bps, price_min_usdc/price_max_usdc, and request_id are left entirely undocumented in both schema and prose. It does not compensate for the coverage gap.

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 says to "Start Create & Sell from a blank goal," which gestures at the tool's function but relies on an internal flow name ("Create & Sell") rather than a plain verb+resource. It never plainly states that this creates a product listing, so an agent must infer the purpose from the tool name and the large family of sibling product_* tools. The purpose is legible but not self-evident.

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 gives one concrete routing rule: to recruit unknown teammates on Collaborate, set team_timeout_minutes to 60-1440 and follow recruit_action. That implies usage context tied to the sibling speedbot_product_recruit, but there is no guidance on when to call product_create versus product_publish, product_amend, product_project, or the other product lifecycle tools. Usage is implied rather than stated.

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