AI Website Security

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so the safety profile is covered. The description adds genuinely new behavioral context: it fetches as an anonymous visitor, stores nothing, is free, and the DNS-filter result is framed as a measured fact about reachability rather than a verdict. It does not discuss rate limits or behavior on fetch failure.

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 verb and resource, then a compact enumeration of return fields in one sentence, closing with the free/no-storage facts and a docs link. The long parenthetical list of headers is dense but each item is informative 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 usefully enumerates what comes back, which is exactly the right compensation, and it adds cost/retention facts and a docs URL. Minor gaps remain around error or unreachable-domain behavior, but nothing essential 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?

Single 'url' parameter with 100% schema description coverage, so the schema already carries the semantics and the description adds no syntax, formatting, or normalization detail beyond it. Baseline 3 per the high-coverage rule.

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?

Specific verb+resource ('Reads the public home page of a website') followed by an explicit enumeration of the returned signals (TLS cert fields, redirect, headers, mixed content, DNS-filter blocking). It also draws the boundary against the sibling paid offering with 'It does not look for malware: that is the paid scan', so an agent can separate it from get_security_offer without opening either 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?

Gives clear usage context: a passive, free, non-storing check of a site's public surface, and explicitly excludes the malware use case by pointing to the paid scan. It never names the sibling tool get_security_offer outright, and does not state prerequisites such as when a URL is invalid or unreachable, so it stops just short of explicit when/when-not routing.

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, idempotentHint, and openWorldHint=false, so the safety profile is covered structurally. The description adds real behavioral context: it enumerates exactly which offers are returned, what each includes, and notes that the purchasing page is where the owner accepts terms and confirms ownership. It does not discuss response shape details beyond content, but adds value over annotations.

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?

A single front-loaded sentence naming the resource first, then the offer list, then the fields returned, closing with a docs URL. It is long but each clause carries distinct information; front-loading is good.

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 must convey what is returned — and it does so thoroughly (offer names, inclusions, price, purchase page). Combined with annotations that cover read-only/idempotent behavior, an agent has everything needed to call and interpret it.

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?

Only one optional parameter (language enum), and schema description coverage is 100%, so the schema fully documents it. The description never mentions language localization, adding nothing beyond the schema — baseline 3 per the high-coverage rule.

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 ('Returns the AI Website Security offers') and enumerates the concrete catalog entries (Record, Record + Restore, Watch, Watch + Restore, Watch Fleet). An agent can tell this is a catalog/offer lookup, distinct from the sibling check_site_security_basics, 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?

Usage is implied by the content — it's the tool to consult for offers, pricing, and purchase destinations — but the description never states when to use this versus check_site_security_basics, nor any prerequisites or exclusions. Adequate but leaves routing to inference.

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