find_multi_supply

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

With no annotations at all, the description carries the full burden and does disclose real behavior: the data source is live Spansh markets, the search breadth is pages x 100 nearest stations with default 4 and max 10, and the result ordering is full-cover first, then most lines covered, then nearest. The remaining gap is that it never says how the search origin is determined, which matters because x/y/z, system_name and journal_dir are all present but unexplained.

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?

Three short sentences, front-loaded with the core promise, followed by the one parameter whose format is non-obvious and the tie-breaking order. The inline JSON example earns its space. Minor looseness in 'pages x 100 nearest stations', which needs the schema to be fully parsed.

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?

An output schema exists, so return-value explanation is rightly omitted, and the ordering rule plus stock disclaimer cover the important behavioral surprises. For a 10-parameter tool at 0% schema coverage, though, it leaves too much unspecified: whether location comes from coordinates, system_name, or the journal directory, and what max_results or the filter flags actually do.

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%, so the description must compensate, and it partially does: it defines the commodities map as name -> minimum supply per load with a concrete example, and explains pages as a multiplier on 100 nearest stations with its default and cap. The other parameters (x/y/z, system_name, journal_dir, max_results, orbital_only, large_pad_only) get no semantics at all, leaving roughly half the calling surface undocumented in both places.

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 a concrete outcome: finding a single station that supplies an entire multi-commodity shopping list from live Spansh market data. That clearly separates it from single-item siblings like find_commodity or station-lookup tools like spansh_search_stations. It stops short of an explicit verb+object phrasing but the resource and scope are unmistakable.

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 context is implied rather than prescribed: it tells you the tool assumes a whole shopping list and warns that stock rotates so results should be verified in-game. It never names an alternative (e.g. find_commodity for a single item, spansh_search_stations for browsing) or states when not to use it.

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