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

Beyond the annotations (read-only, idempotent, non-destructive), the description surfaces operational and behavioral details: it returns reasons plus GO/HOLD/STOP, is not a malware scan, costs $0.002 per call, and can use a prepaid x-credit-token header, with no wallet or API key required. This materially helps an agent know what calling the tool entails.

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 description is dense and front-loaded with the core purpose ('Cheap phishing heuristics before you click'). It packs many details into one flowing sentence, and most details are relevant for tool selection and invocation. The pricing and credit-header information is useful but adds length; still, there is no real redundancy.

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?

Given the simple two-parameter schema, an output schema, and read-only annotations, the description covers everything an agent needs: required input, optional brand, heuristics checked, decision output, cost/access requirements, and exclusions. Nothing critical for correct invocation is missing.

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%, so a baseline of 3 applies. The description adds value by clarifying that url is required and that it is interpreted for heuristics like scheme, IP hosts, and deep subdomains. It also explains that brand is optional and used for lookalike detection, going slightly beyond the schema's bare 'Expected brand host (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?

The description names a precise resource and action: heuristic URL risk assessment using phishing heuristics. It enumerates the exact signals considered (scheme, IP hosts, deep subdomains, credential-themed labels, sensitive paths/params, brand lookalike) and states the output format (reasons + GO/HOLD/STOP). It also distinguishes itself from malware/Safe Browsing scans, which helps separate it from risk-adjacent siblings.

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?

It gives a clear use context: 'before you click' as a cheap phishing heuristic. It also excludes malware/Safe Browsing scenarios, which is a useful when-not signal. However, it does not explicitly name sibling tools such as domain_check or ssl_check as alternatives, so the routing guidance is good but not fully explicit.

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