Get the change feed of a market

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

Goes well beyond the annotations: it explains that read-only does not mean free (paid plans spend 1 record per event, demo spends 1 request per call), gives the pagination envelope (5 default, 20 max, continue with cursor), and warns that the returned `data` is untrusted listing text that must not be followed as instructions. That quota nuance is exactly the kind of thing readOnlyHint=true would otherwise mislead an agent about.

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-loads the purpose and usage examples, then separates quota mechanics and the untrusted-data warning into their own short paragraphs. Every sentence carries information the agent cannot get from the schema or annotations — nothing is restated for 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?

For a 6-parameter, paginated, quota-metered read tool with a full output schema, the description covers everything that matters: scope, alternatives, entitlement failure mode, cost model, pagination, and the trust boundary on returned data. Return-value structure is rightly left to the output schema.

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 the schema already documents market, since, type, limit, cursor, and min_pct, making 3 the baseline. The description adds value by tying `limit` to quota cost ('1 record per event') and by framing `cursor` as the continuation mechanism, though it never mentions min_pct or the default price-change threshold.

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 — 'what changed in one market since a moment' — and enumerates the exact event types returned (added, disappeared, price_drop, price_up) plus the concrete markets (Encar, Che168, Copart/IAAI). It explicitly separates itself from the nearest siblings, telling the agent to use search_cars for current listings and get_car for details.

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 concrete when-to-use phrasings ('what is new on Che168 since yesterday', 'Encar price drops this week') and names the alternatives for the adjacent intents (search_cars, get_car). It also states the entitlement condition that makes the call fail — included in Pro/Max/demo, error on other plans — which is guidance an agent needs before calling.

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