Marketplace Search

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

With annotations declaring readOnlyHint=false, this description does real work: it warns that calls potentially consume paid API credits and require confirm=true, and explains that the read-like POST does not publish to social platforms. It also discloses that creation_time/listing_date_text can be null, that creation_time_descend is unstable across cursor pages, and that date_listed uses calendar-day buckets.

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 purpose and pagination essentials, then caveats. Dense with useful facts and little waste, though the sentences on sort_by and date_listed restate schema text somewhat, making it longer than strictly necessary.

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 15-parameter tool with no output schema, the description covers the key return fields (creation_time, listing_date_text, cursor, has_next_page), pagination mechanics, and behavioral caveats. An agent has enough to page, dedupe, and avoid credit surprises without opening anything else.

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% (baseline 3), and the description still adds meaning: category_id is the numeric FB category ID echoed back in results, cursor must be passed through unchanged, and sort_by/date_listed carry non-obvious server-side behavior. It does not add semantics for the simple filter params (condition, price, radius), which the schema already covers.

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 ('Searches Facebook Marketplace listings') and the key scoping inputs (keyword, lat/lng). It is clearly a search tool, though it never explicitly distinguishes itself from sibling facebook_marketplace_marketplace_location_search or facebook_marketplace_marketplace_item, leaving that routing to inference.

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 strong operational guidance: pass cursor back as-is, continue paging while has_next_page is true and dedupe by listing id for new-item workflows, and confirms that sort/date filters use the same values as the UI. It stops short of stating when to prefer this tool over the location-search or item siblings.

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