facebook_marketplace_search

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

With no annotations, the description carries the full burden and does well: it discloses that access requires no account, that coverage is partial, and a genuinely non-obvious behavior — an empty filtered page may still have a continuation. It omits per-page result limits, rate limiting, and error behavior, which keeps it short of a 5.

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?

Four dense sentences, front-loaded with the account-free search premise followed by filter, coverage, and pagination notes; almost nothing is wasted. The only snag is the 'end_cursor' wording that does not match the schema's 'after' field.

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 10-parameter, no-annotation, no-output-schema tool, the description covers access model, filtering semantics, partial coverage, and pagination edge cases. It stops short of describing the result shape, page size, or the price-string format, which are the practical gaps an agent would hit on first call.

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 0% across 10 parameters, so the description must compensate. It explains radius (km), age via days_since_listed, strict_filters, include_details, and the pagination cursor, but leaves location, min_price, max_price, and sort_by undefined, and refers to 'end_cursor' while the schema parameter is named 'after', creating a naming mismatch the agent must resolve.

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?

The first sentence gives a specific verb and resource ('Search public Facebook Marketplace') plus a distinguishing constraint ('without an account'). It is clearly a listing-search tool, separable from the item-detail sibling, though it never names that sibling explicitly.

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?

The description implies usage through 'Follow opaque end_cursor' and 'Sort all collected pages for newest-first monitoring', which tells the agent how to page and how to assemble results. It does not state when to prefer this tool over facebook_marketplace_item for full item details, nor any prerequisites or exclusions.

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