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

Annotations only declare readOnly=false, idempotent=false, destructive=false, openWorld=true; the description adds far more: the ad is pre-checked and a refused ad costs nothing, returns checkoutUrl and leaseId, the human must pay within 60 minutes, no account is required, and omitted fields are backfilled from the website. This is exactly the non-obvious behavior an agent needs.

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 core action, then the outcome and handoff, so structure is excellent. It is somewhat dense, with several parentheticals carrying payment and timing constraints, but every sentence carries distinct operational information and nothing is pure 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?

An output schema exists and the description still names the two return values (checkoutUrl, leaseId) and the human action they drive. Combined with auth-free operation, payment ownership, the 60-minute limit, and the explicit next tool, an agent has everything needed to invoke this correctly and hand off 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 each parameter is already documented with its fallback behavior, so the schema carries the parameter burden. The description restates the website-backfill and payment-email ownership rules but adds no syntax or format detail beyond the schema, which is the calibrated baseline of 3.

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+resource ('Start leasing a free window or billboard for a brand') and immediately scopes it against siblings by naming check_lease as the required follow-up and implying windowId originates from find_windows. An agent can distinguish it from find_windows/get_window/check_lease without opening any 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?

Gives explicit workflow routing: call this after selecting a slot, then 'follow the lease with check_lease.' It also states preconditions and constraints ('you can't pay for them', 'nothing is charged before they do', 60-minute Stripe window) so the agent knows both when to call it and what it cannot do.

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