Weio site check

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

Annotations already declare readOnly, idempotent, open-world. The description adds real behavioral context beyond that: it silently tests BOTH example.com and www.example.com, and it reports cause codes, a warning flag, certificate expiry, and a plain-English explanation per address. The 'public websites only' restriction is also disclosed. No auth or rate-limit detail, but the safety profile is already covered by 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?

Front-loaded with the core behavior, then the enumerated failure causes and the return shape. One long sentence carries a lot but every clause earns its place; only mild density cost prevents a 5.

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?

There is no output schema, so the description must describe returns and it does: cause code, warning presence, expiry date, and a per-address explanation. Combined with the dual-hostname behavior and the public-site restriction, an agent has everything needed to call it and interpret results.

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 the baseline is 3, but the description adds meaning the schema does not: the single domain input is effectively expanded to two hostnames (apex and www), which materially changes what the agent should expect. It also implicitly accepts domains or full URLs, matching the schema example.

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 and resource: it checks what a browser visitor sees for a domain, covering both the apex and www variants, and enumerates the failure modes it detects. It is unmistakably about HTTPS/certificate health, though it never names or contrasts itself with the sibling site_info, so an agent must infer the boundary.

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 context for when it applies (diagnosing browser security warnings for a domain) and an explicit scope exclusion ('public websites only'). It does not route the agent between this and site_info, which is the one missing piece for a top score.

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, but the description adds substantial context beyond them: the concrete result ceiling (up to 10), index freshness date, current coverage limits, the exact field set returned, and deliberately withheld data (no email addresses or personal data). That is meaningful behavioral disclosure an agent cannot infer from the 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?

Three tightly packed sentences, front-loaded with scope and cap before the return-field and disclaimer details. Coverage limitations are restated in both the first and last sentences, a minor redundancy that keeps it from being maximally efficient.

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 carries the return-value burden and does so, enumerating the record fields (name, website, phone-layout flag, scan/source scope) and the omitted fields. Combined with the coverage and freshness caveats, an agent has everything needed to call it and interpret results correctly.

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 100%, so category, area and limit are already documented in the schema, and the description largely restates the same constraints (10-record cap, Fresno County, dentists). It adds no syntax, format or validation detail beyond the schema. Baseline 3 applies when the schema carries the parameter burden.

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+resource (returns public business records), states the exact scope (dental businesses in Fresno County, CA, scanned 2026-09-30) and the result cap, so an agent knows precisely what this tool yields. The sibling tools (check_https, site_info) are in unrelated domains, so no differentiation is needed. It also proactively forbids misreading it as a directory or ranking.

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 explains the effective usage window via its coverage constraints (currently small, dated index; dentists in Fresno County only) and explicitly warns 'This is not a complete directory or ranking', which tells the agent when results will be sparse or unrepresentative. It stops short of naming alternative tools or explicit when-not-to-call conditions, so it is clear context rather than full routing guidance.

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 readOnly, idempotent and open-world, so the safety profile is covered. The description adds genuinely non-structured context: personal-name addresses are deliberately excluded, only one homepage fetch occurs, and broken HTTPS is flagged. That is meaningful disclosure beyond the 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 dense paragraph that front-loads what is read and what is returned, with the constraint trailing. Every clause carries information, though the parenthetical CMS list and email prefixes make it longer than strictly necessary.

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 carries the full burden of describing return values, and it does so field by field. Combined with annotations covering the safety profile, an agent has everything needed to call this correctly.

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 single 'domain' parameter is fully documented in the schema (domain or URL, with examples). The description adds nothing about accepted input formats, so the baseline 3 is correct — the schema does all 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?

Specific verb+resource: reads a business website's homepage and enumerates exactly what it returns (title, CMS, emails, phone, socials, contact URL). An agent knows precisely what data comes out. It does not explicitly distinguish itself from the sibling check_https, even though the 'flags a broken HTTPS certificate' clause overlaps that tool's territory.

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 closing clause 'Public websites only; one homepage fetch' gives a scoping constraint, and the return list implies use for business/contact enrichment. But there is no explicit when-to-use vs. the sibling check_https, and the HTTPS overlap is unresolved, so routing still requires inference.

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