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

Annotations only declare readOnly=false, destructive=false, idempotent=false, openWorld=false; the description goes far beyond by disclosing side effects (nothing charged, the hour keeps its diamond, the call stays free, the calendar sends an updated invite) and precise refusal reasons (not theirs, cancelled, begun, awaiting calendar, time not open). That is exactly the behavioral context an agent needs before invoking a non-idempotent mutation.

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?

Dense but front-loaded: the operation and its scope come first, then the time-source branching, then side effects, then failure cases. It is a single long paragraph with some run-on nesting (parenthetical id conditions, dual time sources), though almost every clause carries unique information.

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 non-idempotent mutation with no output schema, the description covers purpose, valid inputs per booking kind, side effects, and the full failure surface, and it describes the response shape ('the answer's booking has the new label'). Little an agent needs to call this correctly is missing.

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% and the start/bookingId descriptions already say 'exactly as my_bookings lists it', so the description largely reinforces the schema. It does add genuinely new constraints: pass the start exactly as listed, and refer to the new time by its label rather than a self-computed weekday, which goes beyond the schema text.

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 and resource (move one of the signed-in person's own upcoming bookings) plus the exact target (another open time of the same kind). It implicitly separates this from book_hour_with_ben / book_intro_call (creating new bookings) and cancel_booking, and names my_bookings as the source of ids.

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?

Explicitly says when this applies (bookings from my_bookings where canMove is true) and gives the branch-specific alternative sources of valid start times: openHours for an hour with Ben, introCall.moveTimes for the free intro call. It also enumerates the conditions under which the call is refused, which functions as when-not-to-use guidance.

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