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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), yet the description adds real behavioral context the annotations cannot: count vs total, has_more, the 50 cap, offset paging, and the explicit instruction not to report zero results from a partial slice. It stops short of stating result ordering, locale fallback behavior, or whether total reflects the same filters, so it is strong but not exhaustive.

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 critical, failure-prone information (partial results) is front-loaded in the first two sentences, then purpose, then the sibling exclusion. It is on the long side and repeats the 50 limit and offset paging that the schema already carries, which is the only real waste.

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 10-parameter, zero-required search tool with no output schema, the description covers return contents ('product cards in the requested language with price range, minimum order and the supplier'), pagination semantics, and the downstream routing decision. Nothing an agent needs to call it correctly or to report results honestly 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?

Schema coverage is 100% and the schema already documents every parameter, including the Incoterms 'any match' rule and the 1–50 limit range, so the description is largely restating field names ('free text, category, manufacturer, country of origin, maximum minimum-order quantity, maximum price or delivery basis'). It adds only modest meaning, such as framing price as a range and locale as affecting returned text; the baseline of 3 applies when the schema does the heavy lifting.

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+resource+corpus: 'Search wholesale products published on Gemalli,' followed by the exact filter dimensions. It explicitly separates itself from list_manufacturers by declaring 'this tool returns goods, and a list of goods is not an answer about companies.' An agent can route between the two without opening either 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?

Gives a positive trigger ('when the person is looking for GOODS to buy or source') and an explicit exclusion plus named alternative ('when the question is about the COMPANIES themselves ... use list_manufacturers instead'). It also supplies an interpretation rule for partial slices, which is a usage condition, not just a warning.

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