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

Annotations already cover the safety profile (readOnly, openWorld, idempotent, non-destructive), and the description adds substantial context the agent cannot get elsewhere: a hard cost ($0.01 per call over x402 on Base), the prepaid x-credit-token header for unlimited use, 'no free tier', and 'No API key required'. That is exactly the payment/auth information an agent needs before invoking a metered external tool.

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?

The purpose and payload are front-loaded before the parametric, timing, and pricing details, so an agent can stop reading early. It is slightly padded — 'Ask the live web' followed immediately by 'Search the live web' repeats the same idea, and several sentences carry marketing cadence — but no section is truly wasted.

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, return values need no further explanation, yet the description still summarizes them. It covers scope, timing, parameters, defaults, payment rail, and auth requirements, so nothing an agent needs in order to call this correctly is missing.

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 baseline is 3, but the description goes beyond the terse schema text: it states the maxResults range with its default (1..20, default 5) and explains what includeAnswer=false actually does ('skip the summary and take sources only'). The default value of 5 is not present in the schema, so this is genuine added meaning.

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?

Very specific verb+resource: 'Search the live web' and it names the exact payload (ranked results with title, URL, snippet, relevance score, plus a synthesized one-paragraph answer). It runs long on framing ('Ask the live web... from an agent that has no browser'), and it never distinguishes itself from the closest sibling, exa_search, so it falls short of a 5.

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?

It gives a clear triggering condition — 'The step before reasoning about anything that happened after the model's training cutoff — prices, releases, incidents, docs' — which tells an agent exactly when to reach for it. It does not name alternatives (exa_search, web_extract) or state a when-not-to-use beyond the throwaway 'Nothing crypto about it', so no explicit routing.

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