extract_urls

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

No annotations are provided, so the description carries the burden. It does disclose real behavior beyond the schema: dedupe and preservation of first-seen order, plus a note that it is a verified pure command (implying no side effects). However it omits the return shape and what happens on no matches, which leaves gaps for a tool with zero annotation coverage.

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?

One front-loaded sentence with zero waste; the dedupe/order constraint arrives before the metadata tag. The bracketed conductor tag is mildly noisy but carries a useful purity signal.

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 one-parameter, no-output-schema transform this is nearly complete. The only material omission is the return format (list of URL strings, behavior when none are found), which an agent would want to know.

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?

There is a single parameter, 'text', at 0% schema description coverage, but the description's phrase 'from a text' effectively maps to it and the parameter is self-evident. Little additional semantics are needed.

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 (extract) and resource (http(s) URLs from a text) plus two behavioral qualifiers (dedupe, first-seen order). The resource is distinct enough from siblings like extract_emails and extract_dates, though no sibling is named.

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?

Usage is only implied by the name and the phrase 'from a text'. There is no explicit when-to-use, when-not-to-use, or pointer to adjacent extract_* siblings, leaving the agent to infer selection.

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