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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds the useful trait that results are paginated plus the remediation semantics for each link type. It does not state ordering, default page size, or what 'open' means operationally, but the additions are real and go beyond the annotations.

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?

Four short sentences, front-loaded with what is listed, then remediation routing, then the pagination caveat. Nothing is repeated from the schema and no sentence is filler.

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 and annotations cover the safety profile, so the description only needs to orient the agent; it does that plus remediation paths. Minor tension worth noting: the description says external links must be edited in source content, while the linkType schema says external needs replace_link, so the two remediation stories for external links do not match exactly.

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 page/limit/linkType are already fully documented with defaults and clamping behavior. The description mentions brokenLinkId (not a parameter here) but adds no meaning to the three actual parameters, so the baseline applies.

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+resource ('Open broken links') and names the producing subsystem ('the content-graph link scanner'), so the agent knows this is a read of scanner output rather than a scan operation like run_link_scan. It is clearly separable from fix_broken_links, replace_link, and create_redirect.

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?

Explicitly routes by case: internal links → create_redirect with brokenLinkId, external links → edit source content, many at once → fix_broken_links. That is a full when/when-not/alternative map naming the sibling tools by name.

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