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

Annotations already declare readOnlyHint=true and destuctiveHint=false, so the safety profile is covered and the bar is lower. The description adds a scope qualifier ('attributed external suppliers') plus examples, which gives some domain context, but it leaves 'attributed' undefined (attributed to whom or what?) and says nothing about result ranking, pagination, or match behavior.

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?

One sentence with no fluff is efficient and front-loaded, so there is no waste. But at roughly ten words it is under-specified for a tool with zero schema descriptions and amiguous siblings; a second sentence clarifying params or selection context would be more appropriate for its needs.

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?

The single sentence leaves key gaps: no return-format information (and there is no output schema to fall back on), no parameter semantics, and no differeniation from at least five other search* siblings. For a tool at this complexity with no schema descriptions, the description is not complete enough for reliable selection and invocation.

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 0% schema description coverage, all three parameters (q, limit, capapability) are undocumented by the schema, placing the burden entirely on the description. The examples ('APIs, compute, data and software') loosely hint at capapability values, but q and limit get no meaning — no query syntax, no default or max limit behavior. The description only partially compensates for the coverage gap.

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 uses a specific verb ('Search') and a distinct resource ('attributed external suppliers') with concrete examples ('APIs, compute, data and software'), so an agent can tell what domain it targets. However, it does not explicitly differentiate it from similarly named siblings like search_external_catalog, search_supply_graph, find_capability, or discover_compute, so it falls just short of a 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?

There is no guidance on when to use this tool versus the many search-family siblings (search_external_catalog, search_supply_graph, find_capability, discover_compute, search_global_market). No context, preceditions, or exclusions are provided, so an agent must guess which search tool fits a given scenario.

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