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

Goes well beyond the annotations: it discloses asynchronous collection ('can take several minutes'), the pending-result contract with job_id and next_check_after_seconds, and the credit model ('One read on delivery; pending checks use none'), which explains why readOnlyHint is false for a search. It also states plan gating (Plus/Pro), the 1–10 result ceiling, and that out-of-city results are filtered out.

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 the core purpose, then scope, then return contents, then async/cost behavior – a sensible ordering. It is dense and slightly run-on in the final two clauses about reads and pending checks, but nearly every sentence adds information an agent needs.

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 three-parameter, open-world search with no output schema, the description covers return fields (listing text, price, currency, area, links), exclusion of seller data, result-count bounds, plan requirement, and the full pending-job lifecycle. Nothing material needed to invoke or poll it correctly is missing.

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?

With 0% schema description coverage, the description carries the burden and largely does: 'query' is the item, 'city' should include state or country where names repeat (with an 'Austin, Texas' example), and '1–10 results' bounds the limit parameter. It does not explicitly tie limit to the parameter name or default of 5, leaving a small inference.

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: 'Find public Facebook Marketplace goods by item and city,' which scopes it to Marketplace listings rather than general classifieds or ads. It does not explicitly differentiate from near-siblings like search_classifieds, find_ads, or resale_prices, so an agent must infer the distinction from the 'Facebook Marketplace' framing.

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?

Usage is implied rather than directed: the tool is for locating goods by item and city, and the 'without seller profiles or contact harvesting' clause signals what it is not for. However, no alternative tool is named and no when-to-use-versus-sibling condition is given, even though search_classifieds and find_ads overlap in intent.

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