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

Beyond the readOnly/idempotent annotations, it explains the status state machine (pending = checkout open, processing = bank debit) and clarifies that the booking is confirmed by the gym's Stripe webhook 'either way' — an important caveat that this call does not itself confirm the booking. It doesn't discuss polling cadence or eventual-consistency timing, keeping it short of a 5.

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 tight sentences, front-loaded with what the tool returns, then when to call it, then the webhook caveat. The status list is dense but each item carries meaning; nothing is filler.

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 carries the return burden and does so by naming the statuses and the gym-visibility flag. Only minor gaps remain (no indication of latency or how long a pending state typically lasts).

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 coverage is 100%, so ref and locale are already documented. The description reinforces where ref comes from ('started with book_dropin or join_gym (ref)'), but adds no format or edge-case detail (e.g. expired refs) beyond the schema; baseline 3 applies.

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?

Names the specific resource (status of a purchase created by book_dropin or join_gym) and enumerates the possible outcomes: pending, processing, paid, free, failed, plus whether the gym appears in the person's Gymmy account. This clearly separates it from siblings like book_dropin, join_gym and my_gyms.

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?

States both the trigger ('call it when the person says they paid or asks') and the automatic path ('the widget calls it by itself after the Stripe page opens'), which tells the agent when its own invocation is and isn't needed. No inference is required.

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