extract_links

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, so the safety profile is covered. The description adds genuinely useful output behavior beyond that: results are deduplicated, returned as absolute URLs, and include anchor text. It does not disclose what happens when the link count exceeds the limit (truncation vs. paging), which is the main remaining behavioral unknown.

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?

It is a single short parenthetical fragment with no wasted words, but the terse fragment style leaves it under-specified rather than efficiently structured. A leading verb plus the same parenthetical detail would cost no extra length and read far better.

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?

An output schema exists, so return shape need not be described, and the annotations cover safety. However, the tool is a fetch-and-extract operation whose only tuning knob (limit) is undocumented, and nothing states whether the target URL must be publicly reachable or whether JS-rendered pages are handled — meaningful gaps for an open-world network tool.

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 both parameters (url and limit) rely entirely on their titles, and the description compensates for neither. In particular, the limit parameter with a default of 200 is never explained — the agent cannot tell whether it caps results, truncates silently, or affects ordering.

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 phrase "Internal and external links on a page" identifies the resource clearly, but it is a noun fragment with no verb, so the agent must infer that the tool extracts/returns links rather than summarizing or validating them. It also does not differentiate itself from the nearest sibling, read_url, which presumably returns page content that may include links.

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?

There is no when-to-use guidance and no mention of any alternative such as read_url, page_metadata, or seo_audit. The agent gets no signal about whether to call this instead of read_url when it only needs link data.

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