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

Annotations already declare readOnly, idempotent, and non-open-world behavior, so the safety profile is covered. The description adds real behavioral content beyond that: newest-first ordering, a 24-hour default window, and a hard 30-day lookback cap, which constrain how the agent should call it.

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?

Three dense sentences, each load-bearing: what it returns, why to use it plus the cursor pattern, and the default/limit constraints. The purpose is front-loaded with no 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?

Covers purpose, cursor continuation, time bounds, and category filtering for a 3-param read-only tool with no output schema. The only soft spot is that next_since itself is referenced without being formally documented, but the usage pattern is clear enough to act on.

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 baseline is 3, but the description adds meaning beyond the schema by explaining the cursor workflow (next_since returned by a prior call is fed back as since) and restating the default/lookback semantics for since and optional category filtering.

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 ('List open wanted ads posted since a given time, newest first') with scope, ordering, and an implicit contrast to the sibling search tool ('without re-running a search'). An agent can distinguish it from search_wants immediately.

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 usage context (notice new demand without re-searching) and a concrete operating pattern: remember next_since and pass it back as since. It does not explicitly name search_wants as the alternative for one-off queries, so it stops short of full when/when-not routing.

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