Crypto Link Check

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

Goes beyond the annotations by confirming they hold in practice ('free, read-only, no network fetch') and by disclosing the verdict vocabulary (official | no_red_flags | caution | suspicious | dangerous). It also surfaces cost structure (free here, 0.005 USDC via x402 for the full check), which is genuine behavioral context. It does not explain latency, caching, or what happens on malformed input.

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 the strongest claim (free, read-only, no network) and the action, with detail following. The parenthetical enumerations are dense but each earns its place by defining scope. The upsell clause is the longest single element and sits slightly awkwardly inside a tool description, but it does double duty as the alternative-route signal.

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 correctly compensates by enumerating the verdict values an agent will receive and listing the signal categories that drive them. Cost and the paid escalation path are covered. Missing only failure-mode behavior (what verdict or error an unparseable URL produces).

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 sole parameter already documents 'URL or bare domain'. The description repeats the same 'URL/domain' framing without adding syntax, normalization, or edge-case guidance, so it contributes nothing beyond the schema. Baseline 3 applies when the schema does the work.

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 names a specific verb and resource ('check a URL/domain for crypto phishing signs') and enumerates the exact signals checked (lookalike domains, punycode, free hosting, bait words). It also distinguishes itself from the richer sibling by framing itself as the free pre-connect pre-check, so it is clearly identifiable against full_report_info.

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?

States a concrete trigger context: 'before connecting a wallet or signing'. It also frames the alternative — the paid full check for domain age, DNS, redirects and page scanning — implicitly routing deeper-dive cases elsewhere. It never says when the tool is not appropriate (e.g., non-URL inputs or already-verified domains), which keeps it just short of a 5.

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

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

Annotations already declare readOnlyHint=true, consistent with 'Does not pay', so no contradiction exists. The description does add the useful clarification that no payment is attempted and names the x402 protocol, but it says nothing about what the response contains (price, payment target, steps) or any limits.

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 short sentences, front-loaded with the subject and followed by the key non-behavioral caveat. Nothing is wasted, though the leading fragment lacks an explicit verb, which slightly weakens the lead.

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?

For a zero-parameter info tool with no output schema, the description covers the topic but leaves open what the response actually contains and how it relates to the sibling checking tool. An agent knows roughly what to expect but not enough to describe the result to a user.

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 tool takes zero parameters, so the baseline of 4 applies; there is nothing for the description to disambiguate. It correctly signals a no-input informational call.

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 states the specific subject matter — instructions for purchasing the full link check via x402 — which is distinguishable from the sibling check_crypto_link that presumably performs the check itself. It is a noun-phrase rather than an explicit verb ('returns'), so it is clear but slightly fragmentary.

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?

'Does not pay' implies a when-not condition and hints that this is the informational counterpart to the actual check tool, but there is no explicit statement of when to call this versus check_crypto_link. Usage is inferable rather than stated.

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