netintel_exa_contents

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

With no annotations, the description carries the full burden. It usefully discloses the batch cap (3 URLs), the fallback behavior (index + live crawl), and that results are per-URL with status, which is real behavioral context. It omits auth requirements, rate limits, cost, and failure semantics for blocked URLs.

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?

Dense and front-loaded: capability, mechanism, and return shape arrive in the first two clauses with no filler. The only defect is that the text is cut off mid-sentence, which harms structure.

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?

For a tool with no output schema and no annotations, the description does cover the return shape (title, author, published_date, text, per-URL status) and the crawl strategy well. But with 0% parameter coverage and a truncated tail, an agent still lacks guidance on livecrawl and max_characters.

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 0% across three parameters, so the description must compensate. It adds a batch constraint (up to 3 URLs) not present in the schema, but never explains the 'livecrawl' string parameter or 'max_characters' numeric parameter, leaving two of three parameters undocumented anywhere.

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 ('clean page text for up to 3 URLs in one call') plus the mechanism ('Exa's index + live crawl'). It implicitly distinguishes itself from a direct-fetch sibling by claiming JS-rendered and bot-walled support, but the truncation ('Pairs with…') cuts off the explicit sibling differentiation, so it lands just 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?

The claim that it 'works on JS-rendered and bot-walled pages that direct fetch can't read' implies when to prefer it over a plain fetch tool. However, there is no explicit alternative named, no when-not guidance, and no cost or rate-limit caveats — usage is inferred rather than stated.

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