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

Annotations already declare readOnly/openWorld/no-destructive, but the description adds critical operational behavior they cannot convey: the ~25 second budget, the check_id continuation mechanism, and that the tool works without an account. These are exactly the traits an agent needs to invoke and poll correctly.

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?

Two sentences, no filler, and the scope-and-detections clause is front-loaded before the async caveat. Every clause carries operational information.

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 values need not be described. Combined with the account-free note, the async continuation contract, and the page cap, the description gives an agent everything needed to call and re-call the tool correctly.

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 coverage is 100% and the schema defines both url and check_id, so the baseline is 3. The description goes beyond it by explaining the check_id's role in resuming an in-flight check, which clarifies the intended call pattern rather than just restating the field.

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 (checks) and scope (up to 50 pages from the sitemap) plus the exact conditions it detects: no image, one shared image, or broken pages. This is enough to distinguish it from the sibling check_link_preview, which operates on a single link rather than a whole site.

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 makes the async flow explicit: a call returns in ~25s, and an unfinished check returns a check_id that a later call resumes from. This tells the agent when a second call is needed. It stops short of explicitly naming check_link_preview as the single-page alternative, so usage is implied rather than spelled out.

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