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

With no annotations supplied, the description carries the full burden and does so: it discloses cost (€0.002 per URL), the billing/auth mechanism (API key in Authorization: Bearer), latency bounds (under 15 s deep, under 50 ms shallow), and the return shape (0–1 score, low/medium/high verdict, per-signal evidence). It also discloses the divergence between deep and shallow inspection, which is the main behavioral risk of misuse.

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?

Front-loaded with purpose, then return values, then cost/latency, then a clearly delimited 'Parameters —' section. The signal enumeration is dense but every item adds discriminating information; the only minor waste is restating return values that the output schema already covers.

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 and return details are still summarized, and cost/auth/latency are covered, which is sufficient for a two-parameter read-only scoring tool. Remaining gaps are error behavior for malformed or unreachable URLs and any rate limiting, though neither is critical to correct invocation.

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 0% and the schema types are uninformative (both fields anyOf string/null with null defaults), so the description must compensate and largely does: it explains `url` as the link to check and defines `deep` as true=redirects+WHOIS+TLS+page, false=address only. It does not address the schema/description mismatch (deep typed as string, default null) or that `url` is technically optional.

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: phishing and scam risk scoring of a link from its own signals, explicitly 'without a paid threat feed'. It enumerates the exact signal families checked (typosquatting, homographs, IP hosts, shorteners, redirect chains, domain age, TLS, credential-harvest forms), which clearly separates it from sibling tools like link_preview, domain_health, and url_to_markdown.

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 gives concrete selection criteria for the `deep` mode (follow redirects/WHOIS/TLS/page vs address-only under 50 ms) and makes the paid-per-call tradeoff explicit, which is real usage guidance. It never names a sibling tool or states an explicit exclusion, so the agent must infer that link_preview or url_to_markdown are for non-security fetches.

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