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

The annotations declare readOnlyHint=false, idempotentHint=true, and destructiveHint=false. The description adds a crucial behavioral trait: the side-effect of generating future classes for the booking horizon, which is not implied by the annotations. It also notes that it is only for business owners, which is an authorization requirement not in the annotations. This adds value beyond the annotations, covering a key behavioral consequence that an agent should know before invoking.

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?

The description is two sentences long, concise, and front-loaded with the key constraint ('Only for business owners...') and the main action ('Set when a class runs'). The second sentence adds the important side-effect. There is no waste, and it earns its place. It could be slightly more structured, but it's efficient.

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?

Given the tool's moderate complexity (3 parameters, nested schedule array), the description is short. It does not explain the schedule parameter's structure or how future classes are generated in detail, nor does it mention return values (though no output schema exists). However, the schema provides some structure, and the annotations cover idempotency and safety. For an agent to correctly construct the schedule array, it might need more info on 'days' and 'time' formats, but the schema gives examples. Overall, it's adequate but missing some detail on the schedule parameter and the generation behavior.

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?

The schema description coverage is 33%, meaning only one parameter (business_id) has a description, while schedule and offering_id lack them. The description does not add any parameter-specific meaning, but the schema provides some hints for schedule (e.g., 'days' example) and business_id has a description. The description mentions the purpose but not the parameters' role. Since coverage is low, the description could compensate, but it doesn't. Baseline 3 is appropriate because the schema covers some parameters and the description gives context but not parameter details.

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 clearly states a specific action ('Set when a class runs') on a specific resource ('sessions' implied by the name, but contextually 'class timetable'), and explains a key side-effect: 'future classes are generated for the booking horizon.' This distinguishes it from sibling tools like owner_set_schedule, which likely manages the schedule differently, and from booking tools. The verb 'upsert' is implicit in the name, but the description makes the purpose clear.

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 description gives a clear context for when to use it: 'Only for business owners signed in to Awning.' This implies it's for owners as opposed to customers, aligning with the 'owner_' prefix in siblings. It does not explicitly state when NOT to use it or name alternatives, but the ownership restriction and the action of setting class times are sufficient for an agent to select it over booking or availability tools. There is no explicit exclusion, but the context is clear enough.

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