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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: it explains the change-category semantics (initial is not a check, check confirmed the price, listing is stated not checked), which tells the agent how much trust to place in each event, and it documents the pagination contract.

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?

The purpose and the cursor-continuation rule are front-loaded, and the category glossary is dense but every clause carries distinct meaning. The parenthetical asides are a bit cramped, but no sentence 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 an output schema present, the return shape need not be described, and the critical unknowns for a 6-parameter feed tool (category semantics, cursor continuation) are covered. Remaining gaps are the kinds filter vocabulary and the limit default, which leave a filter-heavy tool slightly under-explained.

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 50%, with since and offer_id and since_time partially documented in the schema, but kinds, categories, and limit undocumented there. The description compensates substantially by defining the meaning of all seven category values, which is the hardest part of this tool to use correctly. It does not explain the 23-value kinds enum or the limit default, so it stops short of full compensation.

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?

"Offers updated, verified or withdrawn since a cursor (or a time)" names a specific verb and resource, and the change-category taxonomy makes clear this is a change-feed rather than a detail fetch. It is distinguishable from get_offer and search_deals without opening the schema. Phrasing is slightly compressed, but the intent is unambiguous.

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?

It gives concrete usage context for continuation ("Pass next_cursor back as since to continue") and implies incremental polling. However, it never says when to prefer this over get_offer or verify_offer, and does not cover the offer_id scoping use case or clarify cursor vs since_time selection trade-offs.

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