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

The description adds minimal behavioral context beyond the readOnlyHint and openWorldHint annotations. It mentions regex filtering but does not disclose return format, handling of duplicates, or whether URLs are absolute or relative. The readOnlyHint already covers safety, so it is not misleading.

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 a single concise sentence with no wasted words. It front-loads the core purpose ('collect all anchor hrefs') and adds the filter condition efficiently.

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?

The tool has no output schema and two undocumented parameters, yet the description only explains one parameter. It does not state the return type, whether links are unique, or what the selector does. The readOnlyHint mitigates some concerns but does not fill these gaps.

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 0%, so the description must compensate. It explains 'pattern' as a regex filter, but the 'selector' parameter is entirely unexplained. This leaves a significant gap for an optional parameter that the agent cannot infer.

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 clearly states the tool collects anchor hrefs, which is a specific action and resource. It differentiates from sibling tools like get_text and get_html by targeting anchor hrefs specifically, and mentions optional regex filtering.

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 implied by the name and description: use when you need to collect links from a page. However, there is no explicit guidance on when to use this vs alternatives like get_html or get_text, and no exclusions or prerequisites are stated.

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