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

Annotations already cover readOnly/idempotent/non-destructive, so the bar is lower, and the description still adds real behavior: an empty list is a valid outcome, and it will not fabricate links to uncrawled pages or edit copy. That tells the agent the output is advisory and bounded by crawl coverage — information not in 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?

Three short sentences, front-loaded with scope. The two negative statements carry weight, though "Does NOT rewrite your copy" is the least necessary of them for a read-only getter.

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 single-param read-only tool with no output schema, the description covers the call precondition and the shape of the result (a list, possibly empty). It stops short of describing what a suggestion item contains, but annotations and the empty-list note make it callable without ambiguity.

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?

One parameter with 100% schema coverage, so the schema already documents crawl_id as coming from crawl_site. The description only reinforces that the crawl must be finished, adding slight meaning above the schema.

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 (internal-link suggestions) and scopes it to a finished crawl, which ties it to crawl_site's output. It doesn't explicitly position itself against siblings like get_crawl_issues, but the resource is distinct enough to select on.

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?

"From a finished crawl" and "empty list when there is nothing real" imply the prerequisite and the empty-result case. There is no explicit when-to-use/when-not statement or named alternative among the many sibling tools.

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