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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds substantial non-obvious behavioral context: per-call pricing ($0.01), the x-credit-token header for prepaid calls, a 1-free-call-per-day allowance, the text=1 result cap at 5 and $0.03 cost, and the '402 challenge' interaction. This exceeds the annotation bar.

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 description is dense and mostly front-loaded, with the core purpose and required input stated early. However, the opening repeats 'Exa's neural web search' twice ('one call at a time — Exa's neural web search, resold per call'), which is mild redundancy. Otherwise every clause 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?

The description covers required input, all parameter semantics, pricing, payment/auth via x-credit-token, free tier, result caps, and the 402 challenge flow. Since an output schema exists, return values need not be restated. No important usage context is missing for a tool of this complexity.

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%, but the schema descriptions are terse. The description adds real semantic value: numResults '1..10 (default 5)', type 'auto|fast|instant', includeDomains 'restricts the search', and text=1 with highlight behavior, cap, and pricing. This is much more than the schema provides.

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?

The description names a specific verb ('search') and resource (Exa's neural web search), and enumerates the output fields: 'title, URL, publish date, author, relevance score'. It also positions the tool against stale knowledge: 'what the web says today, not what a training cutoff remembers', making its scope unambiguous even without naming a sibling.

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?

The description gives clear context for when to use it: 'For agents that need what the web says today, not what a training cutoff remembers.' It also states the required input and parameter constraints. However, it does not name alternative tools or explicitly state when not to use it, so it stops short of a 5.

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