Zovo Website Status Checker

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

Adds substantial context beyond annotations: it makes one live request from the edge network, reports six named headers with an A-F grade, includes TLS, robots.txt, and CSV output, and cannot check private/reserved addresses or page content. This is exactly the operational behavior an agent needs.

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?

Use cases are front-loaded, followed by capabilities and exclusions. It is somewhat dense and repeats the single-address constraint, but most sentences carry useful selection or behavioral information.

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?

Complete for a single-request read-only checker with an output schema: it explains what is checked, what is returned, key limitations, and when not to use it. No critical calling context 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 the baseline is 3. The description adds meaningful semantic constraints for the url parameter: exactly one address at a time and no private or reserved addresses, which the schema does not state.

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: checking HTTPS/security headers for one website. It distinguishes from the sibling by specifying one address at a time and explicitly excluding multi-site checks, matching the likely role of check_websites.

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?

Provides strong when-to-use trigger phrases and clear exclusions (vulnerability tests, more than one site). The alternative bulk-check tool is implied by the multi-site exclusion but is not named explicitly, so it falls short of the highest bar.

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 cover safety (readOnly, idempotent, openWorld, non-destructive), and the description still adds real context beyond them: checks originate from an edge network, up to 10 URLs, results include a CSV download, and a site may block the check. It also discloses hard limits — no IP literals, no private/reserved addresses, only ports 80 and 443 — which the annotations do not convey.

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 user phrasings that should trigger it, followed by capability, then limits and exclusions in a clear order. It is a dense run-on sentence with a long trigger list, but every clause carries routing or constraint information.

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 single-parameter read tool with an output schema and full annotations, the description covers everything an agent needs: what it returns, throughput limit, output format (CSV), and the failure modes that would otherwise cause a wasted call. Return-value detail is a bonus, not a gap.

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 the single 'urls' parameter and its 1–10 bound and accepted formats are already fully documented in the schema. The description's 'for up to 10 URLs' merely restates maxItems, adding no new parameter semantics — baseline 3 applies.

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 ('makes a live request from the edge network') and enumerates the exact verdict fields returned (redirect chain, HTTP status, response time, TLS, page title, security headers). It does not explicitly distinguish itself from the sibling check_security_headers, even though security headers are listed as one of its outputs — overlap an agent must resolve on its own.

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 concrete trigger phrasings ('is it down', 'website status') and explicit exclusions (no monitoring, no uptime history, no internal/private addresses), which is unusually strong routing guidance. It stops short of naming the sibling check_security_headers as the alternative for header-focused queries, so the alternative-selection half of the criteria is incomplete.

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