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

With no annotations provided, the description carries the full burden and delivers: it discloses pricing, boilerplate stripping, format options, max_chars truncation with a truncated flag, and zero cost for failures. It also explains the payment model (USDC, no account, no API key). This goes well beyond basic call semantics.

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 four dense sentences, front-loaded with the core purpose and cost, followed by output details, then edge-case pricing. Every sentence adds distinct operational or behavioral information, with no filler or redundancy.

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 covers the important operational details: output content type, format selection, size cap and truncation flag, and failure pricing. The only minor gap is that it does not specify the exact JSON response envelope or error shape, but an agent still has enough to invoke it correctly.

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. The description mostly restates schema details (e.g., max_chars default and truncation flag) without adding new meaning. It does not explain URL constraints such as http(s) requirement or IP rejection, which are already in the schema. Thus no increase above baseline is warranted.

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 states a specific verb ('Read'), a clear resource ('any web page'), and a concrete output ('clean LLM-ready markdown'). It also positions the tool as 'the natural companion to /web/search', which helps distinguish it from query-based siblings. This is far more specific than a tautology.

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 explicitly frames when to use the tool: after a web search, to read a specific URL's readable core. It also provides useful guidance by noting that unreachable or non-HTML targets cost nothing, encouraging attempts. However, it does not name sibling alternatives like web_crawl or web_search_read, nor does it state when not to use them.

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