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

Annotations already cover read-only/idempotent/open-world safety, and the description adds the non-obvious operational traits: pages may come from a shared cache, and refresh bypasses it at full billing rate. That cost and staleness disclosure is exactly the context annotations cannot carry.

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, no filler, and the structure is front-loaded: capability and return format first, usage routing second, constraints and the refresh trade-off last. Nothing repeats the schema verbatim.

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 two-parameter read tool, everything an agent needs is present: accepted schemes, cache behavior, cost implication of refresh, and the shape of the returned content. No output schema exists, but the description already names what comes back.

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 the baseline is 3; the description earns a bump by explaining *when* to set refresh (page changes often, or cached copy looks stale) rather than merely restating what the flag does. The url parameter's http/https restriction is reinforced in prose as well.

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 web page) and even the return shape (title + main content as Markdown). It is clearly separable from web_search, which is named as the alternative for discovery rather than full-page reads.

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 two concrete selection conditions: a URL the user handed you, or a web_search result whose snippet wasn't sufficient. It also states the constraint that only http/https URLs work, so the agent knows the boundary before calling.

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