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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered; the description adds real value beyond that by disclosing the credit cost (1, or 30 for deep) and the specific behavior of reporting whether a shortener itself disabled, flagged, or removed the link. It omits that deep mode requires an API key, leaving that to the schema.

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?

Roughly two sentences with zero filler: the purpose question is front-loaded, the resolution behavior follows, and the cost caveat is compressed to a fragment at the end. Every clause carries information an agent would otherwise have to guess.

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 an output schema present, return values need not be spelled out, and the description covers the key behavioral facts (redirect chasing, shortener verdicts, cost). The main residual gap is the API-key prerequisite for deep mode, which lives only in the schema rather than the prose.

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 only 50% — the required 'url' parameter has no description at all — so the description has to compensate, and it does partially by explaining what happens to the URL (redirect/shortener resolution). It also adds cost semantics for 'deep' (30 credits) that the schema does not state, though it never clarifies accepted URL formats.

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?

Opens with a concrete question ('Is this link safe to open?') and then names the mechanism: resolves shorteners and redirects and reports the real destination. The resource (a URL/link) is clearly distinct from lookup_domain, lookup_ip, or lookup_shortcode, though it never explicitly contrasts itself with the nearest sibling lookup_shortcode.

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 framing 'Is this link safe to open?' implies the use case (pre-open safety vetting), and the credit note hints at the cost trade-off of the deep mode. However, there is no explicit when-to-use vs. when-not guidance and no named alternative for cases like 'I only have a domain, not a full URL' (lookup_domain).

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