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

Annotations already cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), and the description adds meaningful behavior: draft_id must be retained across turns, one draft_id per business, do not invent missing details, and the multi-turn ask-together-in-one-message rule. It stops short of describing failure modes or validation limits, but the annotation coverage lowers that burden.

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 and audience come first, followed by operational rules in a tight sequence. It is dense and long, but nearly every sentence carries a distinct instruction; a few clauses (e.g. the photos/layout sentence) are incidental rather than essential.

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 multi-turn, interactive intake tool with a large nested schema and no output schema, the description supplies the interaction loop, the response contract ('what was accepted, what is missing, and open_questions'), the clarification policy, and the handoff sequence to owner_preview/owner_submit. Nothing an agent needs to drive the flow correctly is missing.

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?

It explains the three non-obvious top-level parameters (draft_id continuity semantics, new_business, copy_from_business_id) beyond their brief schema notes, and describes the shape of answers at a high level (NL description into structured fields, prices, hours with separate break ranges). The remaining bulk of the nested answers object is left to the schema, whose coverage is only ~50%.

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 names a specific verb and resource ('Guided onboarding', 'Set up a business') and clearly scopes it as a conversational intake flow, distinguishing it from sibling write tools like owner_update_business and owner_submit. It also states the audience constraint ('Only for business owners signed in to Awning') up front.

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 explicit when-to-use routing: repeat until ready_to_submit, then owner_preview, then owner_submit; use owner_photos for images; pass new_business:true for another business or copy_from_business_id for a branch. Alternatives and their selecting conditions are all named.

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