marketplace_compare

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

Annotations only supply readOnlyHint=false and openWorldHint=true; the description adds substantial behavior: dedupe/sold/reposted filtering, like-for-like grouping, price stats, scam heuristics, and latency/page caps. It does not explain why the tool is flagged non-read-only (report/file export as a side effect), leaving one inconsistency in the safety profile unaddressed.

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?

Information-dense and front-loaded: the pipeline and output are stated first, then invocation guidance and constraints. The single run-on sentence is long but every clause carries distinct behavioral information; minor structural cost only.

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 complex 16-param tool with no output schema, the description covers the analysis outputs (price stats, ranked deals, scam flags, opening offer) and operational limits well. It omits mention of the export_report side effect and doesn't describe result shape in detail, but is largely sufficient for correct invocation.

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 16 parameters and only ~50% schema description coverage, the description compensates for some gaps (queries as multi-variant Hebrew/English strings, sorts default and page cap) but is silent on location, radius_km, conditions, price bounds, must_include/exclude, and enrichment depth. Partial compensation against a substantial coverage gap, so a baseline 3.

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 precise verbs and resource: finds best-priced listings, benchmarks the market, and enumerates the full analysis pipeline (merge, dedupe, group, rank, enrich, scam-flag, offer suggestion). Clearly differentiated from siblings like marketplace_search and marketplace_price_history, which do single narrow jobs.

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 invocation guidance: pass several query variants with a Hebrew+English example, default 3 sorts per query, cap of 12 pages, and 5-8s per page timing. It never explicitly names when to prefer marketplace_search or marketplace_price_history instead, so it stays at 4 rather than 5.

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