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

Annotations already declare the safety profile (non-read-only, open-world, non-destructive, non-idempotent), and the description adds substantive context beyond them: the call is free with no x402 payment challenge, the crawl is restricted to the declared domains, the build is queued asynchronously, and an HTTP equivalent endpoint is given. It does not address re-declaration semantics or build latency, which is notable given idempotentHint=false.

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?

Front-loaded with the key facts ('FREE index declaration') and packed with useful detail in a compact space. Slightly redundant in the payment clause ('no payment required: call directly without payment (no x402 challenge; this tool is free)' says the same thing three ways), which is the only thing keeping it from a 5.

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 2-parameter, no-output-schema mutation-ish tool, the description covers purpose, cost, payment/auth posture, crawl scope, and async behavior — enough to call it correctly. It stops short of saying what the caller gets back (job id, status handle) or how long a build takes, which an agent monitoring progress would want given there is no output schema.

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% (domains description covers hostname normalization, maxItems 50), so the baseline is 3. The description earns a bump by adding an ownership constraint not in the schema ('the tenant's own domains') and by stating the operational consequence of the list ('pages fetched from these domains only'), which tells the agent what goes wrong if the list is wrong.

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 ('record the tenant's domains and queue the per-tenant index build') and immediately scopes what the build does (sitemap + Common Crawl CDX discovery over these domains only). It also implicitly separates itself from the sibling cse_search by naming the follow-on 'search tolls $0.01' step, so an agent knows this is the setup call, not the query call.

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 clear workflow ('Tenant submits domains -> index builds -> search tolls $0.01') and an explicit precondition about payment ('call directly without payment, no x402 challenge'), which is the main thing that would otherwise block invocation. It does not explicitly say when NOT to use it (e.g. re-declaration vs. first-time setup, or to use cse_search for querying), leaving that to inference.

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