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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds real value beyond that by enumerating the input domains it refuses (localhost, private networks, authenticated pages), which the agent cannot infer from annotations alone. It stops short of mentioning rate limits, extraction failures, or truncation for huge pages.

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?

Three sentences, each doing distinct work: what it returns, when to call it, and what it rejects. The output format and the tool category come first, so the agent gets the essential distinction immediately.

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?

One required parameter, a full output schema (so return values need no prose), and annotations covering safety. The description supplies exactly the missing pieces: usage trigger and URL admissibility rules. Nothing needed to call it correctly is absent.

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 'url' parameter, so baseline would be 3. The description nevertheless adds constraints beyond the schema's 'Public HTTP or HTTPS webpage URL' by explicitly prohibiting localhost, private-network and authenticated URLs, tightening the meaning of a valid value.

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: 'Extract the readable content of one specific public webpage as LLM-friendly Markdown/text.' It explicitly disclaims search ('This is a page-reading tool, not a search engine'), which cleanly separates it from the sibling tavily_search.

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?

Gives both triggering conditions ('when the user supplies a URL' or 'after tavily_search has found a relevant source that needs detailed inspection') and hard exclusions (localhost, private networks, authenticated/private pages). The alternative is named and the condition selecting it is spelled out.

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

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

Annotations already declare readOnly, idempotent, open-world and non-destructive, so the safety profile is covered; the description usefully adds the return shape and routing behavior. The one loose end is the 'optional short answer', which no parameter exposes and which the description never explains, leaving ambiguity about whether extra synthesis is returned. No contradiction with annotations.

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?

Four short sentences, front-loaded with purpose, then return shape, then routing, then exclusion. The enumeration of research domains is slightly long but does real work in steering query intent.

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?

Since an output schema exists, return values need not be explained in depth, and the usage rules are fully covered. The only gap is the unexplained 'optional short answer' and the absence of any note on result limits/cost of advanced depth, which an agent would benefit from at call time.

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% with enums for topic, timeRange and searchDepth, so the parameters are already well documented. The description adds essentially no parameter-level guidance (e.g., when to favor searchDepth=advanced or how domain filters combine), so the 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 specific verb ('Search the live web') plus the resource domains and the intent ('DISCOVER relevant webpages and source URLs'). It also signals the return shape (ranked titles, URLs, snippets/content), which lets an agent distinguish it from jina_read_url without opening either schema.

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?

Gives explicit when-to-use ('DISCOVER relevant webpages'), names the alternative for the other case ('Use jina_read_url when a specific result needs deeper page extraction'), and states a clear exclusion ('Do not use this tool to read a URL already known to the user'). Nothing is left to inference.

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