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

Annotations already establish read-only, idempotent, non-destructive, open-world behavior, so the bar is lower — and the description still adds meaningful semantic context beyond them: results are unvetted, compliance is 'self-declared' (i.e., not authoritative), and trust/sandbox status must be confirmed separately. That is exactly the kind of caveat an agent needs before presenting providers as trustworthy options.

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?

Two sentences with zero filler: the first front-loads the verb, the resource, and the useful filter facets; the second is a single high-value caveat. Nothing is repeated from annotations or schema.

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 13-parameter, 0%-coverage tool this does a decent job on the disambiguating filters and the trust caveat, and the presence of an output schema removes the need to describe results. Still, an agent calling it blind won't know what 'query', 'capability', 'currency', or 'verified_only' do, or how limit/offset page the results.

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 0%, so the description carries real weight: it names the filterable dimensions (type, region, country served, operating country, data residency with an 'ISO or EU' hint, compliance, pricing model) and crucially distinguishes 'country served' from 'operating country'. But 6 of 13 parameters — query, limit, offset, currency, capability, verified_only — get no meaning at all from either schema or description, leaving a substantial 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?

States a specific verb and resource — 'Find external service providers' — and enumerates concrete provider categories (escrow, payment, insurance, logistics, hosting) plus the dimensions it can be searched by. The scope is unmistakable, though it never distinguishes itself from a sibling like search_agents, so an agent must infer the services-vs-agents split.

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?

'Listing is not an endorsement; check sandbox availability and trust before use' gives real due-diligence guidance and implicitly routes the agent to verification follow-ups (get_listing, verify_attestations). However, it never explicitly names an alternative tool or states when NOT to use this search, so the routing is only implied.

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