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

Annotations already cover read-only/open-world/idempotent/non-destructive, and the description adds substantial beyond-schema behavior: $0.01 per call over x402 on Base, text=1 raising price to $0.03 and capping results at 5, the prepaid x-credit-token path, and the 402 challenge quoting the price. Cost and payment mechanics are exactly the kind of hidden trait an agent must know before calling.

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 and dense with useful facts, but the opening 'Exa's neural web search, one call at a time — Exa's neural web search, resold per call' repeats the same phrase, and the em-dash packing makes pricing and parameter facts compete for attention. Still, every clause except that duplication earns its place.

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 a 5-parameter schema, full description coverage, rich annotations and an output schema, the description covers payment, defaults and parameter interactions adequately. It omits guidance on failure modes beyond the 402 challenge and never positions itself against exa_contents, which would matter for a multi-search-tool surface.

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 the baseline is 3, but the description adds real semantics the schema lacks: numResults default of 5 and its 1..10 bound, the interaction where text=1 caps results at 5, and includeDomains' restricting behavior. It stops short of explaining type=auto vs fast vs instant trade-offs.

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 ('Exa's neural web search') and enumerates the returned fields (title, URL, publish date, author, relevance score), so an agent knows exactly what it gets. It does not explicitly contrast itself with the sibling web_search or exa_contents, so sibling differentiation is left implicit.

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?

Offers a situational cue ('for agents that need what the web says today, not what a training cutoff remembers') and notes no free tier, but never states when to choose this over web_search or exa_contents, nor any when-not conditions. Usage is implied rather than prescribed.

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