Check a deep link domain

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

Annotations declare readOnly/idempotent/non-destructive, but the description goes well beyond them: it discloses the exact network egress (only https://<domain>/.well-known/*, Apple's CDN, Google's API, and the block lists), an SSRF-style safety guard ('refuses domains that resolve to private addresses'), and the ~22 MB first-run block-list download that is cached for a day. These are precisely the runtime traits an agent needs and that the annotations cannot convey.

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 main check enumeration is front-loaded in the first sentence, and scope/network constraints follow. The prose is dense and slightly run-on, but nearly every clause carries distinct information (which files, which CDN/API, which block lists, local execution, private-address refusal) rather than 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?

With no output schema, the description carries the burden of explaining return values, and it does not state what a result looks like (pass/fail per check, verdict format). However, it thoroughly covers input scope, network behavior, caching, and safety, leaving only the response shape as an unaddressed gap for this read-only diagnostic.

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% and the enum values (aasa/assetlinks/adblock) are already fully documented in the schema, including the default. The description mirrors that same mapping (aasa = iOS file + Apple CDN, assetlinks = Android + Google verdict, adblock = EasyPrivacy/AdGuard), so it adds little beyond the structured field. Baseline 3 is appropriate.

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 resource ('a link domain') and then names the exact artifacts it validates: the apple-app-site-association file, assetlinks.json, Apple's CDN copy, Google's Digital Asset Links verdict, and EasyPrivacy/AdGuard block lists. This is unmistakably distinct from the sibling tools (list_links, create_link, search_docs), so an agent can select it without opening the schema.

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 scopes usage clearly: 'Works for any domain, not only DeepLinkNow's,' which tells the agent it is a general diagnostic rather than something tied to the account's own links. It also implies iOS/Android link-readiness is the target scenario. It stops short of explicitly naming alternatives or stating when not to use it, so it earns a solid 4 rather than 5.

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