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

Annotations only declare readOnlyHint and openWorldHint, so the description carries the rest and does it well: JS rendering, the 10-URL batch ceiling, the 20000-character per-URL cap, the truncation/offset continuation workflow, and a real behavioral caveat that markdown conversion mutates structured data such as underscores in JSON keys.

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 sentences, each doing distinct work: capability, batch limit, per-URL limit plus continuation, and the misuse caveat. The core capability is front-loaded and nothing is redundant with the schema beyond necessary reinforcement.

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 no output schema, the description still tells the agent what comes back (clean markdown per URL) and how to interpret and extend a partial result via the truncation header and offset. Nothing needed to invoke 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 a baseline of 3 applies, but the description goes beyond the schema by explaining the functional relationship between the two parameters: each URL is truncated at 20000 characters and the offset parameter is how you continue from the header note. That adds workflow meaning the schema fields only hint at.

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 ('Read web pages as clean markdown, with JavaScript rendered') and immediately differentiates itself from the sibling web_search by describing a direct-read rather than discovery operation. An agent can tell which of the two tools to reach for 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?

The description gives an explicit when-not-to-use case plus the alternative: 'fetch JSON or raw files with a plain HTTP client instead', justified by markdown conversion escaping characters. That is a concrete routing rule with a stated reason, not just an implied context.

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 cover the safety profile (readOnlyHint, openWorldHint), so the bar is lower. The description adds genuinely useful behavior beyond that: the result cap ('up to 10'), the returned fields, and the enrichment for news and papers. It omits anything about ranking behavior or result variability, keeping it below 5.

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?

Two sentences, zero waste. The outcome (what you get back) is front-loaded before the follow-up workflow.

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 no output schema, the description usefully characterizes the return payload, and the schema fully covers inputs. Nothing needed to invoke the tool 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 description coverage is 100%, so the schema fully documents all six parameters including operators, enums, and recency units. The description adds no parameter detail beyond what the schema already provides, which is the correct baseline of 3.

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 ('Search the live web') and immediately distinguishes itself from its only sibling by describing the find-then-fetch workflow. An agent can tell web_search from web_fetch 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?

Explicitly names the alternative ('read them with web_fetch'), giving a clear two-step workflow. It does not state when NOT to use this tool (e.g., for content already fetched), but the routing guidance is unambiguous.

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