WebUpCheck — DNS, Website & Provider Diagnostics

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

Annotations already cover read-only/idempotent/open-world safety, yet the description adds substantial behavioral detail: distinctions between NXDOMAIN, NOERROR-without-records and SERVFAIL, honest admission of partial/truncated evidence, the CDN/caching caveat, quota and cache-window behavior (30s, 5s for partial), keyless auth, and an explicit SSRF-style assurance that it never connects to answer addresses. That is far beyond what the structured fields 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 'Use for...' purpose statement, then layered caveats, all in one dense paragraph. Every clause carries signal, though the caveat/quota tail is dense enough that an agent must read to the end to catch the evidence-quality limits.

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?

An output schema exists, so return-format explanation is unnecessary; the description instead covers the things the schema can't: error-code semantics, partial-evidence handling, caching windows, quota cost, and trustworthiness of record content. Nothing an agent needs to invoke or interpret this correctly appears to be 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 only 50% — the 'name' param is documented in-schema, but the 'type' enum has no schema description. The description compensates by enumerating the record types and stating 'one record type per call (default A)', which is the key semantic an agent needs and is not in the schema.

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?

Opens with a specific verb+resource ('compare A/AAAA/CNAME/NS/MX/TXT/CAA records, TTL, DNS response codes and resolver-reported DNSSEC AD') across two named resolvers, so the scope is unmistakable. It implicitly separates itself from website/DNS-propagation concerns ('not worldwide propagation or multi-geo') but never explicitly contrasts with the sibling check_website, so it falls short of full sibling differentiation.

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?

'Use for public-domain DNS diagnosis' plus the explicit exclusion 'not worldwide propagation or multi-geo' tells the agent both when to reach for this tool and one case to avoid. No sibling alternative is named for the excluded cases, so the routing guidance is clear but not exhaustive.

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/openWorld, and the description adds genuinely new behavioral facts: a 30-second API/MCP shared cache with checkedAt and cached fields to inspect, bounded retry attempts, no API key required, and the interpretive caveat that a blocked or inconclusive result is not proof of a global outage. The caching and retry disclosure is exactly the context annotations cannot carry.

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 usage condition, then output contents, then caveat, then operational notes. No sentence is filler, and the alternative-tool pointer is placed at the end where it does the least harm to the trigger statement.

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?

An output schema exists, so the brief output enumeration is sufficient rather than redundant, and the description supplies the operational details an agent needs: caching window, retry behavior, and how to interpret inconclusive results. Nothing material is missing for a one-parameter read-only probe.

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?

With a single required parameter at 100% schema coverage, the schema already fully documents the url field including the exclusions (no credentials, private addresses, nonstandard ports). The description confirms the target is a public website but adds no format or syntax detail beyond the schema, so the baseline of 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 ('fresh server-side availability observation' of a website) and enumerates concrete outputs: HTTP status, DNS answers, redirect chain, HTTPS connection evidence, timestamps. This clearly separates it from sibling tools like get_service_status that serve curated data.

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?

Explicitly names the trigger ('when a public website will not load') and the alternative for curated data ('use get_service_status'), which is strong routing guidance. It does not mention the sibling check_dns as the cheaper option for a DNS-only question, even though DNS answers are one of its outputs, so one alternative is left unaddressed.

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, openWorld and non-destructive, so safety is covered. The description adds genuinely useful context beyond them: no authentication is performed, a shared refresh limit of once/minute/provider, stale/unavailable reports cannot establish health, and names must be treated as untrusted data. That is solid added value, though the scoring rubric reserves 4-5 for descriptions that go further; here the rate-limit and trust caveats are present but terse, and the return payload's shape is left to the output schema.

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 purpose, then constraints, then caveats; nearly every clause carries operational information. It is telegraphic and dense, with several short declaratives, but nothing is filler and the ordering follows an agent's decision path.

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?

An output schema exists, so return values need not be spelled out, yet the description still signals that responses include official source, age and provider-reported states. Combined with the refresh limit, trust warning and no-match semantics, an agent has everything needed to call and interpret 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 only 50% (the provider enum has no per-value descriptions), so the description must compensate. It lists the supported providers and, for component, clarifies the matching rule — exact ID or case-insensitive substring — plus the critical consequence of a miss ('unknown, never operational'), 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?

Opens with a specific purpose: distinguishing individual product components (Claude API/Claude Code, OpenAI Responses/Chat Completions) from an overall homepage status, and enumerates the supported providers. That scope plus the Google exclusion makes it clearly separable from check_website and get_service_status.

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 both when to use it and when not to: Google component summaries are unsupported, with an explicit redirect to 'its scoped incident feeds' (get_provider_incidents). It also defines the no-match condition ('unknown, never operational'), so an agent knows how to interpret a miss rather than retrying.

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?

Beyond the annotations, the description discloses authentication requirements, shared refresh throttling, freshness handling, return contents, unresolved-entry behavior, Google informational notices, coverage.scope inspection, and untrusted-text handling. This is unusually rich behavioral context for an open-world read tool.

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 key purpose and caveats are front-loaded, and most sentences carry operational value. It is slightly longer than necessary because the provider list duplicates the schema enum and several clauses could be tighter, but there is little wasted content.

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 one-parameter, open-world incident tool with an output schema, the description supplies the important operational context: freshness, staleness semantics, coverage limits, trust boundary, and Google scope separation. An agent has enough information to invoke it correctly without relying on the return schema alone.

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 0%, and the description largely repeats the enum provider names rather than explaining the provider parameter directly. It does add one important semantic distinction: Google sources are separate product scopes, not a single all-Google or Gemini verdict.

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 opens with a specific verb and resource: official active incident reports, scoped to named providers. It is immediately distinguishable from siblings like get_service_status and list_monitored_services because it names the exact provider-status source set and says these are unresolved official entries.

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 clearly establishes when to use the tool: for official active incidents from the listed providers, with explicit cautions that missing/stale data means unknown rather than all-clear. It does not name alternative sibling tools or explicitly state when not to use this tool, so it falls short of full alternative 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 cover safety (readOnly, idempotent, non-destructive, closed-world), and the description adds substantive operational context beyond them: no outbound request to the target, ~15-minute scheduling cadence, a 35-minute staleness threshold, and a 12-sample cap. It also scopes the authority of the data ('not official or global').

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?

Five short sentences, front-loaded with the core action, then the non-probe caveat, then the timing/staleness facts. No filler; each sentence carries a distinct operational fact.

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?

An output schema exists, so return-shape explanation is unnecessary, and the description still flags that samples, freshness, scope, and the status link come back. For a one-parameter cached-read tool, nothing an agent needs before calling 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% and the single enum parameter is already documented as a service ID drawn from list_monitored_services. The description only adds the word 'curated,' which mildly reinforces the fixed enum set but contributes no new syntax or selection guidance beyond the schema.

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 and resource: reads the latest scheduled homepage observation plus up to 12 recent samples for a curated service. It explicitly states what it does NOT do ('Does not make a new request to the target website'), which separates it cleanly from check_website/check_dns 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?

The 'no new probe' framing plus the freshness/staleness numbers tell the agent when cached data is acceptable versus when a live check is needed. 'Not an official or global outage report' excludes the outage-report use case, implicitly pointing at get_provider_incidents, though no sibling is named outright.

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?

Adds substantial context beyond the readOnly/openWorld/idempotent annotations: degraded behavior ('Returns partial evidence if a source is unavailable/rate limited'), cost/auth constraints ('No API key; underlying probe budgets apply'), and a semantic caveat that a reported incident is not proof of cause or attack. It also tells the agent to honor checkedAt/cached/freshness/trust warnings, which shapes how results must be interpreted.

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 trigger condition, then dense supporting constraints; nearly every clause carries operative information. The closing trust-warning sentence is slightly compressed/telegraphic but still earns its place by governing result interpretation.

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 an output schema present, return structure need not be explained, and the description still covers degraded responses and trust signals. For a read-only composite diagnostic with 2 fully documented params, an agent has everything needed to call it and interpret the result.

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 genuine meaning the schema lacks: provider is 'inferred only for known provider-owned hostnames' and should be passed manually for a known dependency hosted elsewhere. That explains the tool's defaulting logic rather than restating the enum.

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?

Clear verb+resource: an evidence-gathering investigation that 'combines one protected HTTP/DNS check, existing homepage history, and optional official provider incidents.' This delineates it as a composite of the granular sibling checks, though it never names those siblings (check_website, check_dns, get_provider_incidents) to make the split explicit.

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 a concrete trigger ('Use when a public endpoint fails and you need evidence-based next steps') plus a conditional routing rule for the provider parameter ('pass provider for a known dependency of another site'). Also states exclusions ('No changes, scans, login or recovery actions'). It stops short of naming the alternative single-purpose tools, so the agent must infer when to use those instead.

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, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds useful behavioral context by stating that this is a curated discovery tool that performs 'No new website probe', though it does not discuss rate limits or underlying data freshness beyond 'curated'.

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 tight sentences, with the discovery scope front-loaded and the sibling-routing guidance immediately following. Every clause adds useful information and there is no redundant restatement.

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 zero parameters, rich annotations, an output schema, and the need to distinguish from several sibling tools, the description supplies everything necessary: what is listed, that no live probe occurs, and which alternatives handle status observations and generic host checks.

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 has zero parameters, so there is nothing for the description to compensate for. Baseline 4 is appropriate for a parameterless tool, and the schema is fully covered.

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 uses a specific verb ('Discover') and enumerates exactly what the tool returns: curated service IDs, homepage URLs, measurement scopes, and official status dashboards. It also explicitly contrasts itself with get_service_status and check_website, so an agent can distinguish its role 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?

It gives explicit routing guidance: use get_service_status for existing observations, and check_website for any public hostname. Combined with 'No new website probe', it clearly establishes when this tool is appropriate and when a sibling is better.

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