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

Annotations only declare the flags (readOnlyHint=false, destructiveHint=false, openWorldHint=false, idempotentHint=false); the description adds real substance on top: the required scope, that the recipient must be signed in as themselves on another surface, and that re-asking replaces the previously issued link. Those are mutation and lifecycle facts not encoded anywhere in the structured fields. It does not disclose expiry or error conditions for an invalid proposal.

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?

Roughly four short sentences, front-loaded with purpose, then permissions, then handling instructions, then lifecycle behavior. Dense and mostly waste-free, though the telegraphic phrasing ('Answers a link for the person to open') costs a little readability.

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 correctly explains what comes back (a URL for the person to open themselves) and how to handle it (pass it unchanged, do not open or forward it), plus the regenerating behavior. The remaining gap is the total silence on the sole input parameter.

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 single parameter proposal_id has 0% schema description coverage, and the description never mentions it — no indication of what a proposal is, where to obtain the id (e.g. from list_booking_proposals or get_booking_proposal), or whether any status gates its validity. With one required parameter the description should carry this meaning, and it does not.

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 ('Get a checkout link') and immediately explains what the link does: sign documents, accept the offer, pay. That distinguishes it from generic link getters like get_link or get_upload_link. It does not explicitly differentiate from the closely-named get_pay_link or get_cancel_link, so an agent still has to infer which link-getter applies.

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?

Gives clear context for use (when a person must sign documents, accept an offer and pay) and names a companion call ('get_link says whether it was used') that covers the follow-up case. It also states the permission needed ('Needs `bookings:write`'). It stops short of naming when NOT to use it versus get_pay_link or send_offer.

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