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

Goes well beyond the annotations: it discloses that each call creates one server-side job record (a side effect, consistent with readOnlyHint=false and idempotentHint=false), guarantees no funds are spent or moved, and specifies the failure mode (structured input_rejected instead of a job). This is exactly the extra context annotations cannot carry.

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 core transformation, then behavior and error semantics in descending priority. Slightly redundant between the opening purpose sentence and the 'Use this when...' sentence, but no padding overall.

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 an output schema present it wisely avoids detailing return fields, yet still covers what an agent needs that the schema does not: the per-call job-record side effect, the no-funds guarantee, immutability of the job, and the input_rejected error path. Nothing material is missing for a pre-payment compile step.

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% for the single parameter, so the schema already defines the query and its length bounds. The description only restates it as a natural-language question, adding no new syntax, format, or constraint detail; baseline 3 applies.

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 concrete transformation: natural-language query -> machine intent + Evidence Pack + one immutable x402 job with a fresh quote pointer. The 'before any payment' framing and the example ('whether a token contract is safe') let an agent distinguish this from the quote/accept siblings.

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 names the condition for use ('when an agent needs to turn a what-would-I-Google question into a priced, quotable evidence job before any payment'), which positions it ahead of the settlement-oriented siblings. It stops short of naming the alternatives (aftersearch_quote, aftersearch_accept) or stating when NOT to use it.

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