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

Beyond the annotations it discloses non-obvious behavior: title matching requires every word given, eBay reports asking prices not sold prices, and each call consumes one read and is saved in the user's Puley history — which explains why readOnlyHint is false despite it being a lookup. It does not cover rate limits or failure behavior, but the cost/state disclosure is exactly the kind of context annotations cannot convey.

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 most important framing (what it is, and the asking-vs-sold distinction) is front-loaded and every clause carries information about a different market. The cost is structure: it reads as one dense run-on paragraph with per-market clauses jammed together, which makes scanning harder than it needs to be.

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?

There is no output schema, so the description must carry the return shape — and it does, listing each eBay listing's price, condition and link, and StockX's last sale, lowest ask, highest bid and 90-day average. Combined with the per-market country constraints and the one-read cost note, an agent has everything needed to call this correctly.

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 description coverage is 0% and there are no enums, yet the description supplies the value sets itself: condition is used/new/any, country is an enumerated eBay site list, and Vinted has its own restricted country list. It also explains the matching semantics of item (all words must appear in the listing title), which is meaning the schema gives nowhere.

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 description states plainly what the tool returns: second-hand selling prices, broken out per market (eBay Buy It Now asking prices, StockX sold prices, Vinted clothing prices). The verb is implicit ('what an item is selling for') rather than an explicit action, and no sibling such as amazon_price_history, search_marketplace or should_i_sell is named to sharpen the boundary, so it lands at 4 rather than 5.

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 useful mode-selection guidance by spelling out what each market value yields (eBay = asking prices, stockx = real sold prices with last sale/lowest ask/highest bid/90-day average, vinted = European second-hand clothes). However it offers no tool-level when-to-use or when-not-to-use guidance against the many price and marketplace siblings, and the 'Asking prices, not sold prices' caveat is a data caveat rather than routing advice.

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