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

Annotations already declare readOnlyHint and openWorldHint, yet the description still adds genuinely non-obvious behavioral context: the tool is paid ($0.015 USDC on Base via x402) and the payment must be supplied in _meta["x402/payment"], which an agent cannot learn from annotations or schema. The "public" constraint further signals it will not work on gated content. Minor gap: no disclosure of fetch-failure, non-HTML, or rate-limit behavior.

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?

Front-loaded with the verb and resource, then output shape, then the concrete example, then pricing. Dense but every element earns its place; the lack of an output schema makes the example payload and payment note worth the length. Slightly run-on in the opening sentence.

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 compensates by giving an explicit example response shape, and it covers the payment/auth prerequisite that would otherwise be a silent failure mode. It stops short of describing edge-case behavior (unreachable URLs, paywalled or JS-heavy pages) or the effect of the `focus` parameter, which for a paid call is a meaningful omission.

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 both `url` and `focus` are already documented in the schema, making 3 the baseline. The description reinforces the URL requirement and shows a URL in the example output, but says nothing about `focus` — arguably the parameter where extra meaning (how a focus question steers the summary) would have most 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 ("Fetch a public web page and return a concise summary") and enumerates the exact output shape: title, 3-7 key points, TL;DR paragraph, entities. It does not explicitly differentiate from the sibling ai_extract, so the agent must infer that summarization differs from structured extraction, but the phrase "gist of a URL" helps.

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?

"Good for research agents that need the gist of a URL cheaply" implies a use case, and "public web page" implicitly excludes authenticated/private URLs. However, no explicit when-to-use vs. when-not, and the obvious alternative (ai_extract) is never named, leaving the routing decision to inference.

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