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

Annotations only declare it a safe, idempotent, closed read; the description goes well beyond that by disclosing quota consumption ("uses the daily records quota"), subscriber-gated fields (links, days on market, price-drop detail), staleness signalling (ingestionStale, lastListingReadAt), and the exclusion rule excludedLikelyTransacted for post-listing registrations of sale/owner change. It also warns that asking prices are never closing prices and defines exactly how askingMedianUsd is computed and why price-on-request aircraft are excluded.

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?

The purpose is front-loaded and the content is dense with no filler, but it is delivered as one very long paragraph mixing filters, output shape, quota caveats, subscriber limits and the social_radar branch. The information all earns its place; the structure would be better served by separating the social_radar branch from the main search.

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 17-parameter, zero-required, open-filter search with an output schema, the description covers what an agent needs to call it and interpret the answer: filters, ready modes, the top-level envelope (total, median, lastListingReadAt), per-row fields, and the two exceptional result shapes. Nothing essential is left to inference.

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 82% schema coverage the baseline is 3, but the description adds real meaning beyond the schema: that mode=new maps to a 7-day detection window, what mode=price_drops actually returns (from/to and the drop date), and that source=social_radar repurposes the whole result set into off-market items with sourceLabel and detectedAt. It leaves uf/region/country, segment, category, limit and cursor entirely to the schema, which is acceptable given the high coverage.

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 opening sentence names a specific verb and resource — "Aircraft FOR SALE across all models in one call" — and scopes the source (tracked portals, one row per aircraft, duplicates merged). It explicitly distinguishes itself from the per-model sibling jt_market_listings, and carves out the alternate result shape when source=social_radar, so an agent can separate this from the other 48 tools without opening a schema.

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?

It gives concrete use contexts — mode=new for "new this week" (last 7 days), mode=price_drops for sellers who lowered asking price, source=social_radar for off-market social-media offers — and routes the per-model/spec-sheet case to jt_market_listings. What is missing is explicit when-not guidance (e.g. for broad fleet counts use jt_global_fleet_search or jt_market_index), so the agent gets positive routing but no exclusions.

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