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

Annotations only claim readOnly and openWorld; the description adds the non-obvious behavioral facts: results are non-deterministic absent `location`, the `location` value can come from a sibling endpoint, and each call costs 1 credit. Cost and determinism are exactly the traits structured fields don't carry, so this materially raises the bar.

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 short sentences, front-loaded with the purpose, then the caveat and cost. Nothing is repeated from the schema verbatim and 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 9 params and no output schema, the description compensates by describing the result shape and the location/determinism interaction. It stops short of covering `cache_max_age` or the sort/price-filter interplay, so it is strong but not fully closed.

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 already 89%, so baseline is 3; the description earns one more by explaining the consequence of omitting `location` and by pointing to /v1/facebook/marketplace/locations as the id source. It leaves `cache_max_age` (the one undocumented param) unexplained and doesn't clarify currency resolution for min/max price beyond the schema's "location's currency".

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 ("Search Marketplace listings") and immediately enumerates what comes back: price, condition flags, location, photos. That return-field list distinguishes it from facebook_marketplaceItem (single listing) and facebook_marketplaceLocations (id lookup) without needing to name them.

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 a concrete conditional rule: without `location`, Facebook picks the city itself and "you do not control" it, so pass `location` for repeatable results. That is real guidance for a common failure mode, though it does not say when to prefer this over facebook_marketplaceItem for a known listing.

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