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

Annotations already declare readOnly/idempotent/non-destructive, so "It changes nothing" is largely redundant. What the description does add beyond structured data is valuable: the state machine semantics and the specific failure mode (missing poll_key yields "not found" rather than an error), which tells the agent to treat absence as a normal outcome. Missing was any hint about response shape beyond the listed fields.

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?

Front-loaded with the action and its use case, then the state enumeration, then the prerequisite — the highest-value constraint (poll_key required) is placed last where it reads as a warning. Three sentences, zero filler; even the parentheticals carry real meaning.

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 two-parameter read-only tool with full annotations and no output schema, the description covers the action, the returnable information (state, psychologist, consent progress, free-move usage), and the auth/prerequisite condition. Nothing an agent needs in order to call it correctly, or to interpret an empty result, is absent.

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 both params are already documented, and the description's only parameter-relevant statement — that poll_key comes from create_booking_draft — restates the schema's own wording ("the poll_key returned by create_booking_draft"). No added syntax, format, or edge-case guidance for ref or poll_key, so 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 a specific verb and resource ("Read a booking's state") and then enumerates every possible state with a plain-language gloss for each (draft = waiting for payment, confirmed = has Meet link, etc.). This is information an agent cannot get from the schema, and it makes the tool instantly distinguishable from cancel_booking_draft or reschedule_booking.

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 customer-facing polling context ("to show the customer") plus the hard prerequisite "REQUIRES the poll_key from create_booking_draft" give clear when-to-use and when-it-fails guidance. It falls short of 5 because it never explicitly contrasts with siblings — it does not say, e.g., that cancel/reschedule are separate tools — leaving the agent to infer that this tool only observes.

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