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

Carries far more than the annotations: discloses paid invocation ($0.01/call), the exact x402 flow (call unpaid to receive PaymentRequired, retry with payment at _meta["x402/payment"]), the alternate HTTP endpoint, and the empty-result contract. This clarifies why readOnlyHint is false despite being a search, resolving what would otherwise be a confusing annotation.

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?

Purpose and scope are front-loaded in the first clause, with payment mechanics trailing. Dense but nearly every clause carries operational content; the 'Honest empty results (items: [])' parenthetical is slightly informal yet does real work by preventing retry loops on legitimately empty results.

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?

With no output schema, the description compensates by listing the result fields (title, link, snippet, indexed_at, display_link) and explaining indexed_at semantically. Payment, preflight alternative, result shape, and empty behavior are all covered, so an agent has everything needed to invoke it correctly on the first attempt.

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 the schema already documents q, tenant_id, and max_results bounds and defaults. The description restates the parameter set and adds only the 'declared domains' framing of tenant_id; it gives no query syntax, matching behavior, or phrasing guidance beyond what the schema supplies.

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 ('site-restricted search ... Google CSE shape over our own per-tenant pre-index') and pins the exact scope ('the tenant's declared domains only'), which cleanly separates it from open-web siblings like news_search or cited_answer_search. The shape notation {tenant_id, q, max_results?} -> {items: [...]} lets an agent see inputs and outputs in one line.

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?

Explicitly offers a when-to-use-this-instead path: a free preflight endpoint that reports tenant index state 'without searching', giving the agent a cheaper alternative before paying. It lacks guidance on when to prefer this over sibling search tools or how to recover from an unbuilt index, so it stops short of full when/when-not coverage.

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