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

Beyond the readOnly/idempotent annotations, the description discloses the computation source (totals already stored on each class, not a per-class roster), the in-progress vs upcoming split, local-time handling via a cached site lookup, and the API cost model (1 site lookup cached, then 1 call per 200 classes, max 11). Cost and timezone behavior are exactly the traits annotations cannot carry.

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 first sentence is long and clause-stacked, but no sentence is filler — scope, exclusions, sibling routing, and cost each appear once. Slightly tighter sentence splitting would improve front-loading of the core 'what you get' claim.

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?

With no output schema, the description still names the key returned values (notSignedInPct, upcomingBooked), the population it aggregates over, and the exclusions. For a read-only reporting tool of this complexity, an agent has everything needed to call it correctly and interpret the result.

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 100% and the schema already documents range, dates, the 31-day cap, and the 'do not pass range as well' rule, so the description clears the baseline. It adds only indirect meaning (the studio's clock governs what counts as started), with no extra detail on date formats or site selection beyond the schema.

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 output (class names and programs attended, plus notSignedInPct) and is explicit about the resource being class bookings/sign-in totals rather than rosters. It also states the boundary 'Classes only: appointments and enrollments are not counted,' which lets an agent separate it from appointment and enrollment siblings without opening a 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 explicitly routes to alternatives: 'class_attendance_summary is fill and busiest times' and 'find_likely_attendees is who to expect,' plus a clear exclusion of appointments and enrollments. Combined with the 'already started on the studio's clock / upcomingBooked' distinction, an agent knows both when to pick this tool and how its range is interpreted.

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