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

Annotations only cover safety flags (non-read-only, non-idempotent, non-destructive); the description adds real behavior the annotations can't convey — on a live business the new offering is immediately bookable, and the agent must confirm details with the owner and never invent a price. It still doesn't describe error cases or what the response contains.

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 hard eligibility constraint front-loaded and no filler. 'Described the same way as in owner_setup' is terse but does work; the cautionary instruction is placed last, which is acceptable.

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?

No output schema, so return values need not be explained, and the description covers auth, the live-business consequence, and a data-integrity caution. However, for a mutation tool whose payload is a large nested object with many optional fields, the absence of any structural or validation guidance leaves a real gap.

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?

Reported schema description coverage is 0%, so the description carries the burden, but it offers no field-level guidance at all — it only points at owner_setup ('described the same way as in owner_setup'), making the agent depend on another tool's schema to know what an offering looks like. The nested offering object with price/units/capacity/schedule/options is left entirely unexplained in prose.

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+resource ('Add a new offering to a business') and scopes it with 'a business the owner already has,' which implicitly separates it from owner_setup. It does not explicitly name owner_update_offering or other siblings, so an agent must infer the add-vs-update boundary.

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?

Gives a clear eligibility gate ('Only for business owners signed in to Awning') and a context condition ('live or not'), which tells the agent when the tool applies. It never names the alternative for modifying an existing offering (owner_update_offering), so the routing guidance is incomplete.

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