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

With no annotations present, the description carries the full burden and does so unusually well: exact price and chain ($0.01 USDC on Base via x402), settlement ordering (paid before the search runs), failover path (Serping → Serper) with its retry cost, and the failure-refund behavior (fee becomes Ghost service credit, not an on-chain refund). It also bounds the DSSE receipt's meaning — it proves what was returned and by which upstream, not accuracy or currency — and flags that a funded payment path via x402-proxy is unverified.

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 purpose before payment mechanics and caveats, which is the right order for a paid tool. It is on the long side and repeats the payment point ('ONE payment' up front, then a full Payment paragraph, then 'there is no second payment'), which costs some density but each block is informative rather than filler.

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?

No output schema exists, but the description describes the return shape (normalised organic hits plus answer box, knowledge panel, related questions) and the receipt artifact, covering what an agent needs to interpret results. Combined with the cost, failure-mode and refund disclosures, nothing material is missing for correct 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?

Schema description coverage is 100%, so query, country, language, results and payment_signature are already documented in the schema, which sets the baseline at 3. The description adds context about payment timing but nothing extra about the search-shaping parameters (e.g., how country/language interact or what 'results' counts).

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 ('Search the web and get the results') and enumerates the returned payload (organic hits with title/url/snippet, answer box, knowledge panel, related questions). It also scopes negatively ('Search only: Ghost does not fetch the pages'). However, it never names or contrasts the sibling tools (ghost_commerce_search, ghost_commerce_vet), so an agent must infer the boundary from names alone.

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?

Clear usage context: one call performs one paid search, the payment is settled before the search runs, and clients like x402-proxy pay automatically while others must pass payment_signature. It also warns to set spendLimitPerTx/spendLimitDaily before use. It stops short of explicit when-to-use-this-vs-ghost_commerce_search routing, so 4 rather than 5.

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