FernTool Network Tools

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

No annotations are provided, so the description carries the full behavioral burden. It discloses that data is cached for ~60 seconds and defines the possible level values, which are useful. However, it does not mention return format, error handling, or whether the service list is fixed (though the enum implies it).

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 a single efficient sentence that front-loads the core functionality (live status) followed by service names and cache detail. Every part earns its place with no 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 no output schema, the description adequately explains what the tool returns (status levels) and cache behavior. It could be more complete by specifying return structure or whether the service parameter can be omitted, but it covers the essentials for a simple status-check tool.

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 schema shows one optional parameter 'service' with an enum of six values, and the description lists the same services. The description adds that the service names map to the official status pages, but does not explain the default behavior when the parameter is omitted (since it is not required). With 0% schema description coverage, the description partially compensates by naming the services, but a baseline of 4 is appropriate for a single enum parameter.

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 clearly states it returns the live status of specific AI services from their official status pages. It specifies the exact services covered and the metric (level), making the purpose unambiguous. It is distinct from all sibling tools, which are unrelated to AI service monitoring.

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 implies usage for checking current availability, but does not explicitly state when to use this tool versus alternatives or what conditions warrant its use. There are no sibling tools that offer similar functionality, so guidance is less critical, but explicit usage context is absent.

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?

With no annotations, the description carries the burden and does so well: it discloses the verdict taxonomy (verified/unverified/suspicious), clarifies that SPF/DKIM/DMARC are 'recorded by the receiving provider' rather than independently re-checked, and states 'Nothing is stored,' covering the privacy/retention question. It omits failure behavior on malformed headers and any rate-limit or auth notes, which keeps it from a 5.

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 decision question followed by input instructions, then the return contents, so the reader gets the essentials first. The long enumeration of returned fields is justified because no output schema exists, though it is a single dense sentence that could be broken into a short list for faster scanning.

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 tool with no output schema and no annotations, everything needed to call it correctly is present: what input to supply, where to get it, what the response contains, the verdict categories, and the no-storage guarantee. Nothing material 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?

There is a single required parameter fully documented by the schema (raw header text), so the schema baseline applies. The description adds real value beyond the schema by explaining where users obtain raw headers in Gmail and Outlook and that the whole raw block (not just From) is expected. No format or size limits are given.

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 concrete question and a specific verb+resource: analyze raw email headers to judge authenticity, then enumerates exactly what is produced (sender identity, SPF/DKIM/DMARC, look-alike names, Received hops, sending IP, verdict). An agent can immediately tell this is a header forensics tool rather than a DNS or IP tool. It does not explicitly name the neighboring email-related tool (check_email_security), so sibling differentiation is left implicit through the raw-header input requirement.

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 clear usage context ('Is this email real or fake?') and practical acquisition instructions (Gmail Show original, Outlook View message details), which is exactly the context an agent needs to gather the input. There is no explicit 'when not to use' or named alternative for domain-level checks, so it stops short of 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?

With no annotations, the description carries the full behavioral burden. It usefully enumerates the fields each result contains (version, scope, country, timezone, ASN, owner, flags), which is valuable since there is no output schema, but it says nothing about rate limits, auth, invalid-input handling, or partial-failure behavior in a batch call.

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 tightly written sentences with zero waste. The scope constraint is front-loaded and the return-field inventory follows immediately, making the whole definition skimmable.

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 batch tool with no output schema, the description covers purpose, cardinality, accepted formats, and return fields — enough to call it correctly. It stops short of covering error/partial-failure semantics, which is the only meaningful remaining 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 coverage is 0% and there is one parameter, so the description must compensate. It does so by clarifying the accepted format (IPv4/IPv6) and cardinality (1-100), matching the schema's minItems/maxItems constraints and adding the address-family detail the schema lacks.

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 (Look up), resource (IPv4/IPv6 addresses), and scope (1-100 at once). The 'at once' phrasing plus the cardinality range lets an agent distinguish it from the sibling single-address tool lookup_ip 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?

The batch scope and 1-100 range clearly signal this is the tool for looking up many addresses, implicitly steering single-address work to lookup_ip. However, it never explicitly names an alternative or states a when-not condition, so it falls short of a full routing instruction.

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?

With no annotations, the description carries the full burden and does well: it discloses the query strategy (authoritative server when reachable, otherwise public resolvers over DoH), names all 8 resolvers, and states that results are marked up-to-date with remaining TTL for stale answers. It does not cover failure behavior when resolvers time out or expected latency, which keeps it below a 5.

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 with the purpose stated first and supporting detail after. The parenthetical and embedded resolver list make it dense, but every clause (authoritative source, DoH, staleness marking, TTL) adds real 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 2-parameter tool with no annotations and no output schema, the description supplies the output shape (per-source up-to-date markers, remaining TTL) and the query mechanism, which is the important missing context. Only the record-type parameter and timeout/failure handling are left unaddressed.

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%: `type` carries a schema note ('default A') but `domain` has no schema description. The description never mentions that the record type is selectable, so it fails to compensate for the gap. It does implicitly clarify that `domain` is the name whose propagation is compared rather than an arbitrary query target.

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 ('Check whether a DNS change has spread') and goes further to describe the mechanism: querying the authoritative NS plus 8 named public resolvers. This is clearly distinguishable from the sibling dns_lookup, which performs a plain lookup rather than a propagation comparison.

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 scenario is implied ('whether a DNS change has spread'), which points to post-change verification, but there is no explicit when-to-use statement, no mention of when dns_lookup or reverse_dns would be the better choice, and no prerequisites (e.g., that the change must already be published).

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?

With no annotations, the description carries the full burden and largely succeeds: it discloses read scope (SPF lookup-limit counting and include following, DMARC policy/pct/reports and parent-domain inheritance, DKIM selector probing, MX-based provider detection) and the return shape. It omits operational traits like rate limits, failure modes, or timeout/caching behavior.

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?

One dense sentence, front-loaded with the agent-facing question, then the mechanism, then the output. No filler and no repetition of the schema.

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, and the description compensates by specifying the return (a protected/partial/unprotected verdict plus exact TXT records to add), so an agent knows what to expect. It is complete on inputs and outputs but silent on error handling and cost/latency, which a network-check tool could reasonably mention.

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 already 100%, so the baseline is 3, but the description adds real meaning: it explains that 'selector' is only needed when not probing common selectors, implying a fallback scan when omitted, and that 'domain' also accepts the DKIM-curated lookups for email addresses. That is value beyond the schema text.

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 the exact question the tool answers ("Can someone fake (spoof) email from a domain?") and then names the specific resources it reads: SPF, DMARC, DKIM, MX. This distinguishes it cleanly from generic siblings like dns_lookup and check_dns_propagation.

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 framing makes the use case unambiguous — auditing a domain's email spoofability — which is clear context for selection. It stops short of naming alternatives or stating when-not to use it (e.g. for raw record retrieval), so it falls short of a 5.

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?

With no annotations, the description carries the burden and does well: it discloses that redirects are followed, which data sources are consulted (RDAP), and the four verdict values (no_signs, mostly_ok, caution, likely_scam). It omits failure behavior (unreachable URL, timeout), latency, and rate limits, so the agent cannot predict edge cases.

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 the question and then packs the evidence list and the verdict vocabulary with no filler. The closing scope disclaimer earns its place by preventing misreadings.

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?

Absent an output schema, the description responsibly enumerates the return signals and enum values, which is what an agent needs to interpret results. Residual gaps are error/unreachable handling and confidence/limitations beyond the malware disclaimer.

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 real value by stating that redirects (including shorteners, per the schema's bit.ly example) are resolved, meaning the input need not be the final destination. It does not discuss malformed URLs or whether bare domains are normalized.

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 question ('Is this website legit or a scam?') and enumerates the exact signals returned (RDAP domain age, look-alike brands, risky TLDs, DMARC, HTTPS), which makes it unmistakable against siblings like check_website_status or whois_lookup. It also bounds scope explicitly: 'Warning signs only; not a malware scan.'

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 context is clear from the framing question, and one exclusion is stated ('not a malware scan'), which steers agents away from expecting payload analysis. It does not, however, name an alternative tool or state when a simpler status/DNS check would suffice 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?

With no annotations provided, the description carries the full behavioral burden and does so well: it discloses the 10-second timeout, Cloudflare edge vantage point, single-request scope, 30-second caching, and the return verdict/reason fields. The 'one vantage point only' warning is especially valuable for interpreting negative results. This is unusually complete behavioral disclosure.

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 definition is front-loaded with the agent's likely question and then efficiently packs timeout, mechanism, return values, and limitations into a compact paragraph. Every phrase adds operational value, and there is no redundant restatement of the name or schema.

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?

Because there is no output schema, the description must explain what comes back, and it does: verdict, reason codes, HTTP status, response time, final URL, and server country/network. It also covers the key limitation of a single vantage point and the 30-second cache. Nothing essential for correct interpretation 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 description coverage is 100% for the single url parameter, so the schema already documents the accepted format and example. The description does not add syntax, format constraints, or edge-case handling beyond what the schema provides. The baseline of 3 is therefore appropriate.

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 the specific question it answers, 'Is a website down?', then names the exact behavior: DNS resolution plus a single URL load. It returns a website availability verdict, which distinguishes it from generic DNS tools like dns_lookup and from service-specific tools like ai_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?

The question framing gives clear context for when to use the tool: checking whether a website is reachable. It also adds the important caveat that results come from one vantage point and are cached for 30 seconds, which helps an agent interpret results. It does not explicitly name when to prefer this over check_dns_propagation or dns_lookup, so it falls short of a full routing guide.

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?

With no annotations, the description carries the burden and does well: it discloses that the unit (seconds/ms/µs/ns) is auto-detected, that time-zone rules apply to offset-less dates, and that extra fields (weekday, ISO week, relative time) are returned. It omits any note on ambiguous or out-of-range input handling, but that is a modest gap for a pure-computation 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?

Two sentences, both essential: the first defines the bidirectional conversion, the second covers the secondary return values. Front-loaded with the primary purpose and free of 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?

For a two-parameter utility with no output schema and no annotations, the description covers input formats, unit detection, timezone semantics, and the returned fields. Nothing an agent needs to invoke it correctly 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, but the description adds real meaning: it explains unit auto-detection for `value` (absent from the schema) and clarifies that `timezone` governs display plus offset-less dates while an explicit offset in the input wins. That precedence rule is behavioral detail beyond the schema text.

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 states a specific verb (convert) with both directions spelled out: Unix timestamp (sec/ms/µs/ns, auto-detected) → readable date, and date/time string → Unix timestamp. This is unambiguous and clearly differentiates it from siblings like date_calc (arithmetic) and get_current_time (clock reading).

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 accepted input formats rather than explicitly stated. It never says when to prefer this over date_calc or get_current_time, nor does it warn about ambiguous inputs, so the agent must infer routing from the tool name alone.

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?

No annotations are provided, so the description carries the full behavioral burden. It does disclose that DST is applied and enumerates the return fields (local date, time, offset, abbreviation, hour difference, day shift), which is genuine value. It says nothing about failure modes (invalid zone, ambiguous abbreviation), limits, or the maxItems cap already in the 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?

Three sentences, front-loaded with the purpose and justification, then accepted input formats, then the return shape. No filler; every clause adds information an agent needs.

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 return values, and all three parameters are addressed. The main residual gap is the absence of error/edge-case behavior for a tool with no annotations to fall back on, but for this simple read-only conversion the coverage is close to complete.

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 baseline is 3, but the description goes beyond the terse schema text: it specifies the accepted from/to notations (IANA zones, common abbreviations with disambiguations like 'IST=India, CST=US Central', or big-city names) and clarifies that omitting time means 'now'. This is meaningful semantics the schema alone does not convey.

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 ('Convert a time between time zones') with the meaningful qualifier that DST is applied. An agent immediately understands the operation. However, it never distinguishes itself from the sibling convert_timestamp, which an agent could plausibly reach for instead.

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 parenthetical '(you cannot do this reliably yourself)' implicitly argues for using this tool over manual reasoning, and 'Omit time for now' gives a usage hint. But there is no explicit when-to-use vs. convert_timestamp/date_calc routing or stated exclusions, leaving the boundary with siblings to inference.

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?

No annotations are provided, so the description carries the full disclosure burden. It does well on outcomes - it names the derived metrics (reading/speaking time, top repeated words) and implies determinism via 'Exactly count' - but says nothing about input size limits, how whitespace/HTML/markdown is handled, or tokenization rules.

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 sentences, zero filler, with the capability list front-loaded and the routing advice ('use this instead of estimating') placed at the end where it functions as a decision cue.

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 usefully enumerates what comes back (counts, reading/speaking time, top words). For a single-input stateless tool this is nearly sufficient; only input limits and text-format handling are left unstated.

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?

One parameter ('text') with 0% schema description coverage, so the description must compensate: it says counts are computed 'in a text', which confirms the parameter's role but not its accepted format or any edge-case behavior. Adequate but thin for the single undocumented input.

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 (count) plus a full enumeration of the resources counted (words, characters with/without spaces, sentences, paragraphs) and the derived outputs (reading time, most repeated words). No sibling tool does anything similar, so no differentiation is required for an agent to select it.

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 instructs 'Use this instead of estimating counts yourself', which gives a clear condition for invoking it over the agent's own arithmetic. It stops short of stating exclusions or limits (e.g. max input length) but the when-to-use signal is unambiguous.

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?

With no annotations, the description carries the full burden and does disclose meaningful behavior: negative values subtract, business_days=true skips weekends, and the return content of each mode (days, weeks, months+days, weekdays, weekend days, resulting date and weekday). It omits what happens on conflicting inputs (e.g. both end and add_days supplied) and invalid date handling, keeping it from a 5.

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 dense sentences, front-loaded with the core purpose before the mode breakdown, with no filler. The telegraphic parentheticals are compact rather than bloated, though the mode pairing takes a moment to parse.

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 9-parameter, no-output-schema tool, the description covers both operating modes and their return shapes adequately, and defaults for start/timezone/include_end live in the schema. Missing edge-case guidance (mutually exclusive parameters, invalid ranges) leaves a modest 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 coverage is only 56% and four numeric params (add_days/add_weeks/add_months/add_years) have no descriptions at all; the description compensates by explaining sign semantics ('negative to subtract') and mode interaction. It leaves include_end and timezone behavior to the schema, so it adds value but does not fully close the coverage gap.

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 states a specific verb+resource ('Exact calendar maths') and then splits it into two concrete modes: interval measurement (with 'end') and date shifting (with add_days/add_weeks/add_months/add_years). It does not name or contrast against siblings like convert_timestamp or get_current_time, which holds it below a 5.

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 guidance is implied through mode-by-mode phrasing ('With end: ... With add_days...:'), which tells the agent how to pick parameters but not when to prefer this tool over convert_timestamp or get_current_time. 'Use this instead of counting days yourself' is a nudge, not explicit when/when-not criteria.

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?

With no annotations, the description carries the full burden. It does add real context beyond the name — the Cloudflare 1.1.1.1 DoH backend and the 'default: all' type behavior — but says nothing about whether the operation is purely read-only, how failures (NXDOMAIN, timeouts, rate limits) surface, or what the response contains.

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 compact sentences with zero filler; the operation and backend come first, followed immediately by the parameter detail. Nothing is padded or repeated.

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 and no annotations, so the description is the only source of behavioral information — yet it never describes the return shape (records, answers, TTLs) or error behavior. For a network lookup tool this leaves a meaningful 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 0%, so the description must compensate. It fully documents the 'types' parameter (allowed values plus default), though the schema enum already lists those values. The required 'domain' parameter gets no format guidance at all — subdomains, trailing dots, or IDN handling are unaddressed.

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 gives a specific verb and resource ('Resolve DNS records for a domain') and even names the resolver backend. It implicitly distinguishes itself from siblings like lookup_ip and reverse_dns by operating on a domain name, but never explicitly brackets what this tool is not for.

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 purpose statement — an agent can infer this is the tool for forward DNS resolution on a domain — but there is no explicit when-to-use or when-not-to-use guidance and no mention of alternatives such as reverse_dns or whois_lookup for adjacent lookups.

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?

With no annotations, the description carries the full burden. It does disclose a genuinely useful behavioral caveat ('Token counts are approximate'), the model coverage, and that the result includes context-window fit, but says nothing about whether it performs live API calls, pricing data freshness, or any rate/auth constraints.

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 purpose front-loaded and no boilerplate. The approximation caveat and input-mode hint both earn their place, though the sentence fragment 'Pass text, or tokens directly' is slightly clipped.

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 3-parameter calculator tool with no annotations and no output schema, the description covers purpose, model scope, cost, context-window fit, and accuracy caveat. Gaps remain around the text-vs-tokens relationship and what the returned estimate looks like, which for an unannotated tool is a meaningful omission.

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 33% (just output_tokens), so the description must compensate. It partly does by clarifying that text and tokens are alternative input modes ('Pass text, or tokens directly'), but it doesn't state whether they are mutually exclusive, what happens if both are passed, or what unit/encoding 'tokens' assumes.

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 specific verb+resource: 'Estimate token count and USD API cost of a text across major AI models', naming the model families and the context-window fit dimension. It implicitly separates itself from the closest sibling (count_words) because it covers cost and model context windows, not just word counting, but it never acknowledges that overlapping sibling explicitly.

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?

'Pass text, or tokens directly' tells the agent how to invoke it but not when to prefer it over count_words or when a cost estimate is the right call. Usage is only implied by the tool's purpose, with no when/when-not or 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?

With no annotations, the description carries the full burden and does so well: it discloses the optional read of current SPF/MX, preservation of unknown entries, drop warnings, live lookup counting against the 10-lookup limit, and the contents of the response. The only gap is that it never explicitly says whether the record is published or merely returned, though 'Returns the record' strongly implies generation-only.

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 purpose, then behavior, then return values. The long service-id list is verbose but justified because the schema defines no enums for `services`, so the ids exist nowhere else.

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 5-parameter, zero-required, no-output-schema, no-annotation tool, the description covers inputs, side effects, limits, and return contents including the starter DMARC record. Minor omissions (behavior when `domain` is absent, interaction between `services` and `includes`) keep it short of complete.

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 60% (domain and strict are documented there), and the description compensates for the undocumented ones: it enumerates the full set of valid service ids for `services`, explains that `ips` and `includes` add extra entries, and notes that `domain` triggers a read of the current record. That is meaningful added meaning beyond the bare array/string types.

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 artifact: 'Build one valid SPF TXT record for a domain from the services that send its email.' That is clearly distinct from siblings like check_email_security or dns_lookup, which inspect rather than generate records.

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 operational context: feed it sending services, optionally let it read the existing SPF/MX, and it will warn before dropping unknown entries. It stops short of naming alternatives (e.g., check_email_security for auditing an existing record) or stating exclusions, so it is context-rich but not a full when/when-not guide.

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?

With no annotations provided, the description carries the disclosure burden and does so well on the return side: it enumerates Unix seconds/milliseconds, ISO 8601 in both UTC and the requested zone, weekday, ISO week, and day of year. It omits that the call is side-effect free and needs no auth, but for a pure clock read that gap is minor rather than risky.

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 sentences, front-loaded with the purpose before the return payload. Every clause earns its place: the return-field enumeration is the most useful part and it is not padded with 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?

There is no output schema, so the description must explain return values, and it does so concretely for every field the caller would otherwise have to discover empirically. Combined with the schema's documented default of UTC, an agent has everything needed to call and consume 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 description coverage is 100% and the single timezone parameter is fully documented in the schema with an example and its UTC default, so the description need only confirm it. It does reference "the requested IANA time zone," but adds no syntax or format detail beyond the schema, which is the expected baseline.

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 ("Get the exact current date and time") that is immediately distinguishable from siblings like date_calc, convert_timestamp, and date_calc, which manipulate rather than report time. Nothing about the intent is ambiguous.

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 parenthetical "(you cannot know it otherwise)" implicitly directs the agent to call this rather than guess the time, which is a real usage signal. However, it names no alternatives and gives no when-not guidance, even though convert_timestamp and date_calc sit adjacent in the sibling list and could plausibly be confused with it.

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?

No annotations, so the description carries the full burden; it does disclose the exact information returned and the important behavioral caveat that a remote agent sees the MCP server host's IP, not its own. It does not mention side effects, rate limits, or whether the lookup requires external network access, which a no-annotation read tool ideally would.

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 sentences, no filler, with the return-value summary and the caller-scoping caveat front-loaded in that order. Every clause earns its place.

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 appropriately enumerates the return fields, and the remote-agent caveat covers the one ambiguity that would otherwise cause misuse. Nothing needed to call it correctly 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?

The tool takes zero parameters, so there is no parameter semantics to explain; the baseline for a 0-param tool is 4. The description correctly implies no arguments are needed.

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 ('Return the public IP address... of the caller') and enumerates the returned fields (ISP, ASN, location, timezone). This implicitly but clearly separates it from lookup_ip/batch_lookup_ip, which look up arbitrary addresses rather than the caller's 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?

"of the caller" establishes the condition that selects this tool over the sibling lookup_ip/whois_lookup tools, and the remote-agent note clarifies when the result may be surprising. It stops short of explicitly naming an alternative or stating when not to use it.

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?

With no annotations, the description carries the full disclosure burden. It usefully names the data sources (DB-IP Lite, IPtoASN) and enumerates returned fields, which signals a read-only enrichment lookup, but it omits rate limits, behavior on unparseable input, and whether a lookup can fail for unknown addresses.

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 sentence that front-loads the action and then lists the return payload, with the parenthetical source attribution adding provenance rather than noise. Nothing is redundant, though the enumeration is long enough that it borders on cramming several payload concepts into one clause.

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 correctly compensates by enumerating the returned fields (version, scope, country, ASN, owner). It is nearly complete for a one-parameter lookup, missing only edge-case behavior such as invalid-IP errors or unresolvable private-range lookups.

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 'ip' parameter is already documented as 'IPv4 or IPv6 address'. The description restates the same accepted formats without adding syntax, normalization, or CIDR-handling detail, so the schema does the heavy lifting and 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?

The description gives a specific verb and resource plus an explicit return payload (version, scope, country, ASN, owner), so the enrichment intent is clear. It fails to differentiate from siblings, however: it leads with 'Validate', which overlaps directly with the sibling validate_ip, and the ASN/owner data also overlaps with whois_lookup, so an agent cannot cleanly separate this tool from those without inspecting schemas.

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?

There is no statement of when to use this tool versus validate_ip, whois_lookup, batch_lookup_ip, or get_my_ip. The only cue is implicit in the return fields. An agent gets no explicit routing guidance despite a crowded sibling set with adjacent purposes.

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?

With no annotations provided, the description carries the full behavioral burden and discloses important traits: the code is static and never expires, input is capped at 2000 characters, and output is an SVG string plus a ferntool.com image URL. It does not discuss rate limits, authentication, or storage side effects, which are minor gaps for a simple generator.

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 dense sentences with the purpose, supported inputs, input limit, and return values front-loaded. Every clause adds useful information and there is no 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?

There is no output schema, but the description explains the return format (SVG string plus ferntool.com URL). There are no annotations, but for a simple static QR generator the key constraints and outputs are covered, leaving only minor omissions such as error-correction behavior beyond the schema.

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 only 50%, so the description must compensate. It meaningfully explains the required 'text' parameter by listing accepted formats and the 2000-character maximum. The optional 'ecc' parameter is already documented in the schema, so combined coverage is good, though the description itself does not discuss error correction.

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 ('Create a static QR code') plus supported payload types and the 2000-character limit. An agent can immediately tell this generates QR codes rather than performing network, DNS, or text-analysis operations like the sibling tools.

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 gives clear usage context by listing accepted inputs: URLs, Wi-Fi strings, mailto:, tel:, and arbitrary text. It does not explicitly state exclusions or compare to alternatives, but there are no sibling QR-generation tools to disambiguate from.

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?

With no annotations, the description must carry the behavioral load, and it does add real substance: cryptographic security guarantees, the weighting rule ('an item listed twice has twice the chance unless dedupe=true'), and the fairness motivation. It omits return format, pagination/limits, and what happens when the item count is not divisible by the requested team count despite promising 'even teams'.

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 sentences, front-loaded with the core capability, then use cases, then the one non-obvious caveat. No filler and no restatement of the tool name or schema fields.

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 5-parameter tool with no annotations and no output schema, the description covers purpose, use cases, fairness mechanism and weighting behavior well. The gap is that it never describes what comes back (e.g. winners list vs. shuffled array vs. team groupings) and glosses over uneven-team edge cases, which an agent must infer.

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 semantics the schema does not state: that duplicates act as weights and that dedupe=true overrides that weighting. It also implicitly frames mode selection through the three named operations, tying 'pick', 'shuffle' and 'teams' to concrete intents.

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 three concrete operations (pick winners, shuffle, split into teams) against a named resource ('a list'), with the qualifier 'fairly' and the mechanism 'cryptographically secure generator'. This clearly separates it from the random_number sibling, which produces values rather than selecting from user-supplied items.

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 use scenarios ('giveaways, raffles, who goes first, random order or team splits') and even explains why the agent needs it ('you cannot choose fairly at random yourself'). It does not, however, name or exclude any alternative tool, so the agent gets context but no explicit routing rule.

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?

With no annotations, the description carries the full burden and discloses important behavioral traits: cryptographic security, fairness, inclusive min/max bounds, and unique-mode semantics. It omits how count and sort affect the result, and does not mention output format or the 1000-count limit, but covers the most critical traits.

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 short, front-loaded with the core purpose, and every sentence adds value: security context, inclusive bounds, unique mode, and concrete examples for coin flip and dice. No wasted words.

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 5-parameter tool with no annotations and no output schema, the description is only partially complete. It covers purpose, bounds, unique mode, and examples, but leaves count and sort behavior unexplained and does not clarify return values, which an agent may need when invoking with non-default count.

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 60%, so the description must compensate. It clarifies min/max inclusiveness and unique=true meaning, which the schema does not. However, it does not explain the sort parameter or the count parameter's effect (e.g., returning multiple integers).

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 states exactly what the tool returns: fair, cryptographically secure random integers. It distinguishes the tool from all siblings, which are unrelated utilities, and even explains why an agent should use it (you cannot produce real randomness yourself).

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 clear contexts for parameter usage: unique=true for raffles, lotto, picking winners; coin flip with min 0, max 1; dice with min 1, max 6. No explicit when-not-to-use or alternative tool is named, but no sibling tool offers this functionality.

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?

With no annotations, the description must carry the behavioral burden. It does disclose a non-obvious trait: the forward-confirmation check (FCrDNS), which hints at extra work and a possible mismatch result. It says nothing about failure behavior when no PTR or FC mismatch occurs, nor about latency or rate limits.

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?

One sentence, front-loaded with the operation, with zero filler. Every clause (reverse/PTR, IPv4/IPv6, forward-confirmation) earns its place.

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?

No output schema and no annotations, so the description is the only source of information. It does not say what is returned (PTR hostname, FC confirmation status, what a mismatch looks like), which an agent needs to interpret results for a lookup tool.

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 0% and the lone 'ip' parameter is only typed as string, so the description must compensate. It does, by specifying that the accepted values are IPv4 or IPv6 addresses, which the schema does not say. That is meaningful added semantics for a single trivial parameter.

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: a reverse DNS (PTR) lookup for an IPv4/IPv6 address. That is far more precise than the sibling names lookup_ip or dns_lookup, though it never explicitly names those siblings to disambiguate the forward-vs-reverse distinction.

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 'reverse DNS (PTR) lookup' versus the forward-looking dns_lookup sibling, but there is no explicit when-to-use or when-not-to-use statement and no alternative named. An agent can infer the intent but gets no 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?

No annotations are provided, so the description carries the full behavioral burden. It faithfully lists the computed return fields and discloses the split truncation rule ('first 64 listed plus the total count'), which is useful. However, it does not state that this is a pure local computation with no network calls, nor how invalid or malformed CIDR input is handled.

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 sentences, front-loaded with the core capability and appended with the optional behavior. Every clause carries distinct information with no 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?

There is no output schema, so the description's enumeration of returned fields is exactly the right compensation. Combined with the schema's parameter examples, an agent has enough to invoke it correctly; only error/edge-case behavior for invalid CIDRs 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 both parameters are already documented with examples in the schema. The description only re-illustrates the split use case ('the /64s in a /48') without adding semantics the schema lacks, so 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?

Names a specific resource (IPv4/IPv6 CIDR) and operation (subnet calculation), then enumerates exactly what it computes: network, netmask, wildcard, broadcast, first/last host, totals, block type. This is clearly distinguishable from the sibling lookup/validation tools (validate_ip, lookup_ip, batch_lookup_ip), which resolve addresses rather than compute subnet math.

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 purpose implies usage (you have a CIDR and want its derived fields), and the split option is illustrated with a concrete case ('the /64s in a /48'). But there is no explicit statement of when to prefer this over validate_ip or lookup_ip, and no exclusions or error conditions mentioned.

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?

With no annotations, the description carries the full burden and does so well: it enumerates the exact warning signals returned, discloses operational limits (max 10 hops, 60 s cache), and states the scope exclusion for malware scanning. An agent knows what it gets back, how deep it goes, and how fresh the result is before calling.

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 a purpose question, then dense but relevant detail on outputs, warnings, and limits. No filler sentences, though the parenthetical enumeration of redirect types and warning signals is long enough to slow scanning slightly.

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, non-destructive read tool with no output schema, the description fully specifies inputs, returned fields (chain, status codes, final URL, title, warnings, tracking-stripped URL), and boundaries. Nothing an agent needs to call it correctly 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% for the single url parameter and the schema already supplies examples. The description reinforces the accepted input shapes (bit.ly-style short links, tracking links) but adds no format or validation detail beyond the schema, so 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?

Specific verb+resource ('follows a URL hop by hop') with an explicit scope statement of what the output contains (each redirect, status codes, final URL, title, warnings). Clearly distinguishable from siblings like whois_lookup or check_website_status, which cover registration and availability rather than the redirect chain.

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 usage contexts (short links, tracking links, QR code links) and one explicit when-not boundary ('Does not scan pages for malware'). It stops short of naming sibling tools such as whois_lookup or check_website_status as follow-ups for domain or uptime questions, so routing is inferred rather than stated.

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?

With no annotations, the description must carry the behavioral burden. The phrasing 'Check whether' implies a side-effect-free read, and it discloses accepted formats (IPv4/IPv6), but it says nothing about the return shape, whether it rejects malformed input or returns false, or what 'classify' means.

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?

One tight sentence with the operation front-loaded and no filler. Every clause ('valid IPv4 or IPv6', 'classify it') contributes meaning.

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 trivial one-param function this is close to adequate, but since there is no output schema the description should specify what 'classify' returns (e.g. private/public/loopback) and how invalid input is reported. Those gaps matter more because no structured field fills them.

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 single parameter has 0% schema description coverage, so the schema only tells the agent the input is a string. The description compensates partially by stating the string should be an IPv4 or IPv6 address, but adds no syntax details (CIDR, port suffixes, leading zeros).

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 ('Check whether') and resource ('a string is a valid IPv4 or IPv6 address') plus the extra outcome ('classify it'). This distinguishes it functionally from the lookup/dns/whois siblings, but the description never names an alternative, so sibling differentiation is implicit rather than 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?

There is no guidance on when to call this versus lookup_ip, subnet_calc, or dns_lookup. An agent could reasonably wonder whether validate_ip also returns metadata or handles CIDR notation, and the description leaves that to inference.

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?

With no annotations, the description carries the full burden, and it does disclose per-input return content (registrar, created/expiry, status, nameservers, DNSSEC; network range, org, country, abuse contact). It omits operational behavior such as rate limiting, lookup failures for unregistered domains, or RDAP server coverage. For a low-risk public read, this is solid but not exhaustive.

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 with the resource type stated first and the parenthetical field lists carrying dense, non-redundant detail. No filler or repetition.

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 only one parameter, no annotations, and no output schema, the description's enumeration of returned fields is what makes the tool usable without a return schema. It is nearly complete, losing only on unsupported-lookup or rate-limit behavior.

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?

One parameter with 100% schema description coverage, so the schema already documents that 'query' accepts a domain, IPv4/IPv6, or ASN with the AS13335 example. The description restates this same information rather than adding format constraints or normalization rules, so it adds little 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?

The description names a specific verb (WHOIS via RDAP) and enumerates the three resource types it accepts and the exact fields it returns for each, so the purpose is unambiguous. It does not, however, reference any sibling tool (e.g. lookup_ip, reverse_dns, dns_lookup), so an agent must infer the boundary from the RDAP field list alone.

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 only implied: the accepted input forms (domain, IP, ASN) suggest when the tool applies, but there is no explicit statement of when to prefer it over lookup_ip or dns_lookup, and no mention of exclusions or prerequisites. No guidance on invalid input or unsupported TLDs either.

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