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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds the temporal behavior 'since previous crawl,' but does not elaborate on what happens if no previous crawl exists, pagination, or output format. The 'v1 stub' caveat is a small extra disclosure, but overall the description contributes limited behavioral context beyond 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?

The description is a single, front-loaded sentence that immediately states the tool's purpose. The parenthetical '(v1 stub)' is a useful minimalist caveat. No word is wasted, making it highly concise and appropriately structured.

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?

With a single parameter, no output schema, and rich safety annotations, the tool is relatively simple. However, the description does not explain what 'links' refers to (e.g., backlinks, referring domains), how 'previous crawl' is determined, or what the response contains. It is minimally complete for invocation but leaves important contextual 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?

The schema has 0% description coverage, and the description does not elaborate on the 'domain' parameter. While the name is self-explanatory in context, there is no guidance on format (e.g., domain with or without protocol, subdomains) or how it relates to the crawl state. The tool description fails to compensate for the missing schema information.

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 'Get links gained since previous crawl' clearly identifies the verb (get), the resource (links), and the specific temporal scope (since previous crawl). This distinguishes it from sibling tools like get_lost_links (lost links) and get_link_velocity (rate of links), making the purpose unambiguous.

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?

The description provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites (e.g., having a previous crawl), nor does it explain when to prefer this over get_backlinks or get_link_velocity. The only hint is 'v1 stub,' which implies limited functionality but offers no actionable comparison.

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