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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description goes well beyond them with latency expectations ('Takes about 11 s; allow a 30 s timeout'), a $0.002 USDC x402 charge with the critical caveat that 'failed calls are not charged,' and the subtle behavior that the state filter only narrows the returned 25 rather than the full match universe. However, it does not describe pagination or how to reach results beyond the top 25, so it stops short of full behavioral disclosure.

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 paragraph is front-loaded with purpose and the output-field list reads efficiently, but the field enumeration (tier, verified flag, coordinates, bands, capabilities, brands, products) partly duplicates what the output schema already declares. The timing, pricing, and sibling-routing sentences all earn their place, while the field inventory is the weakest use of space.

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?

Cost model, latency budget, output contents, filter semantics, and sibling routing are all present, and an output schema exists so return-format explanation is not required. The remaining gap is behavior beyond the top-25 cap — an agent cannot tell from this definition whether more results are obtainable at all, which matters for a tool returning a fixed-size result set.

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%, so all three parameters are documented in the schema itself, setting the baseline at 3. The description earns an extra point by clarifying the non-obvious semantics of 'state' — that it filters the top-25 result set, not the underlying corpus — which changes how an agent should interpret a filtered call. The 'limit' parameter is left to the schema, which is acceptable given full 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 description opens with a specific verb-and-resource framing — 'US and Canadian industrial suppliers from Thomasnet for a product or service term' — and immediately grounds it with examples ('valves, CNC machining'). It enumerates the returned fields (ID, name, type, tier, verified flag, coordinates, phone, website, bands, capabilities, brands, products, total match count), which makes the resource unambiguous and clearly separable from a generic business search.

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 explicitly routes agents elsewhere by naming conditions: b2b_indiamart 'when you need Indian wholesale suppliers and manufacturers on IndiaMART' and b2b_bbb 'when you need Better Business Bureau search: finds businesses by name.' It also states where the state filter applies ('Optional state filter on those 25'), so an agent knows the filter is a narrowing step rather than a full-database query.

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